© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 50915
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    sentence-ending periods (full stops), especially in formal license or documentation text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     -->↵
    -0.07
    ysql
    -0.07
    一封信
    -0.07
    Navigation
    -0.06
     layui
    -0.06
    蕭
    -0.06
     imageSize
    -0.06
    @Test
    -0.06
     위원님
    -0.06
    BCM
    -0.06
    POSITIVE LOGITS
    .
    0.14
    。
    0.13
    ,
    0.09
    ).
    0.09
     .
    0.09
    ．
    0.08
    wój
    0.08
    ?
    0.08
     peeled
    0.08
    ".
    0.08
    Activations Density 2.294%

    No Known Activations