© 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. 19-RESID-POST-AA
    11. 69946
    Prev
    Next
    INDEX
    Explanations

    We

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dred
    -0.07
    Benefits
    -0.07
    꾀
    -0.07
    ʊ
    -0.07
    鄃
    -0.07
    เหมาะ
    -0.07
    artisanlib
    -0.07
    เกร
    -0.07
    orget
    -0.07
    .setVerticalGroup
    -0.07
    POSITIVE LOGITS
     soc
    0.08
    页
    0.08
    ond
    0.07
    可以
    0.07
    在一起
    0.07
    noch
    0.07
     Perc
    0.07
     cuộc
    0.07
    陌
    0.07
     fid
    0.07
    Activations Density 0.117%

    No Known Activations