© 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. 11-RESID-POST-AA
    11. 68093
    Prev
    Next
    INDEX
    Explanations

    Story beginnings

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umericUpDown
    -0.07
    ”.↵↵
    -0.07
    mounted
    -0.07
    _datas
    -0.06
    藨
    -0.06
    芒果
    -0.06
    บรรยากาศ
    -0.06
    渰
    -0.06
     Conor
    -0.06
    inema
    -0.06
    POSITIVE LOGITS
     Wolf
    0.08
     vampire
    0.07
     outliers
    0.07
    უ
    0.07
     Hait
    0.07
    ☛
    0.06
    更换
    0.06
     OTHER
    0.06
     Former
    0.06
    .Suppress
    0.06
    Activations Density 0.150%

    No Known Activations