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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 102645
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rray
    -0.08
    Col
    -0.08
    �
    -0.07
     rollout
    -0.07
    (tab
    -0.07
    ollar
    -0.07
    _Char
    -0.07
    مرا
    -0.07
     질문
    -0.06
    ANA
    -0.06
    POSITIVE LOGITS
    secutive
    0.08
     unchanged
    0.07
     אשר
    0.07
    /]
    0.07
     Greatest
    0.07
    GeneratedValue
    0.07
    Compact
    0.07
     likeness
    0.07
    퍈
    0.07
    (typeof
    0.07
    Activations Density 0.036%

    No Known Activations