© 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. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150831
    Prev
    Next
    INDEX
    Explanations

    Harvey

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    overe
    -0.30
    åĸĻ
    -0.26
    uring
    -0.26
    yr
    -0.26
    ä¸ĢåĪĩ
    -0.25
     TTL
    -0.24
    纶
    -0.24
    离
    -0.24
     ************************************************************************
    -0.24
    pee
    -0.24
    POSITIVE LOGITS
    éľľ
    0.27
    æľĪ以æĿ¥
    0.25
    outu
    0.25
    MSN
    0.24
    Deal
    0.24
    åįĪé¤IJ
    0.24
    deal
    0.24
    heits
    0.24
     Sessions
    0.24
    .onload
    0.24
    Activations Density 0.194%

    No Known Activations