© 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. 15-RESID-POST-AA
    11. 127077
    Prev
    Next
    INDEX
    Explanations

    en

    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_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
    Negative Logits
     NSLocalizedString
    -0.09
    Serialization
    -0.07
    *u
    -0.07
    /Typography
    -0.07
    フ�
    -0.07
    .Formatting
    -0.07
    .AlertDialog
    -0.07
    惕
    -0.07
    стью
    -0.07
    _asset
    -0.07
    POSITIVE LOGITS
     en
    0.08
    注入
    0.08
     défini
    0.07
    勺
    0.07
     por
    0.07
     si
    0.07
    En
    0.07
    ורה
    0.07
    一会儿
    0.07
     específ
    0.07
    Activations Density 0.009%

    No Known Activations