© 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
    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. 124094
    Prev
    Next
    INDEX
    Explanations

    LC/EC/IC

    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
     הבאים
    -0.09
    條
    -0.08
     seizing
    -0.07
     reg
    -0.07
     את
    -0.07
     pulses
    -0.07
     integral
    -0.07
    $('
    -0.07
     restrained
    -0.07
    动作
    -0.07
    POSITIVE LOGITS
    毗
    0.07
    }")↵
    0.07
    🚼
    0.07
     Dummy
    0.07
     bytecode
    0.07
     uploading
    0.07
    电流
    0.07
    ꍲ
    0.07
    ocht
    0.07
    _OBJC
    0.06
    Activations Density 0.005%

    No Known Activations