© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 115777
    Prev
    Next
    INDEX
    Explanations

    vaccine

    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
    .Success
    -0.07
    hổ
    -0.07
     Ethnic
    -0.07
    вшего
    -0.06
    频频
    -0.06
    né
    -0.06
     Tennis
    -0.06
    وكالة
    -0.06
     besides
    -0.06
     lush
    -0.06
    POSITIVE LOGITS
     stairs
    0.08
    暧昧
    0.07
     datos
    0.07
     atrib
    0.07
     trọng
    0.07
     marrow
    0.07
     certify
    0.07
     preocup
    0.07
    玩意
    0.07
    ぜひ
    0.06
    Activations Density 0.004%

    No Known Activations