© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121261
    Prev
    Next
    INDEX
    Explanations

    Expressing doubts

    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
    Negative Logits
    pure
    -0.07
     esi
    -0.07
    这对
    -0.07
     grazing
    -0.07
    ⠩
    -0.07
     Speaking
    -0.07
     לכל
    -0.07
    㬮
    -0.06
    —and
    -0.06
     growers
    -0.06
    POSITIVE LOGITS
    类似
    0.08
     Firstly
    0.07
    �
    0.07
     duro
    0.07
    /library
    0.07
    🛠
    0.07
    是一种
    0.07
     outliers
    0.07
    截图
    0.07
     Diablo
    0.06
    Activations Density 0.042%

    No Known Activations