© 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. 12-TRANSCODER-HP
    7. 23538
    Prev
    Next
    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¡Ĺ头
    -0.28
    ongsTo
    -0.28
    éľĸ
    -0.26
    ivi
    -0.26
    shint
    -0.24
    åĪĨå¼Ģ
    -0.24
    åīį线
    -0.24
    éļ¼
    -0.24
     separating
    -0.24
     Street
    -0.23
    POSITIVE LOGITS
     Institution
    0.30
    ĪæĿĥ
    0.28
    ulg
    0.27
    institution
    0.26
    OOM
    0.25
     Instrument
    0.25
    CISION
    0.24
    æ´¹
    0.24
     persisted
    0.24
    rets
    0.24
    Activations Density 0.001%

    No Known Activations