© 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. 15-RESID-POST-AA
    11. 44651
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Hulu
    -0.07
     TextEditingController
    -0.07
    TextView
    -0.07
     Drinking
    -0.07
    .render
    -0.07
     Cutter
    -0.07
     baptism
    -0.07
    raphic
    -0.07
     Hunger
    -0.07
    enever
    -0.07
    POSITIVE LOGITS
    辿
    0.07
    _ANT
    0.07
     colle
    0.07
    ㅐ
    0.07
    _pct
    0.07
    对方
    0.07
    нул
    0.07
     공간
    0.06
    Fair
    0.06
     paired
    0.06
    Activations Density 0.060%

    No Known Activations