© 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. 9-TRANSCODER-HP
    7. 29962
    Prev
    Next
    INDEX
    Explanations

    general articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宪
    -0.28
    -cond
    -0.28
    诱人
    -0.27
    utters
    -0.26
    à¤Ĩ
    -0.25
     Kö
    -0.25
     RESP
    -0.24
    OTO
    -0.24
    esan
    -0.23
    çĭ¸
    -0.23
    POSITIVE LOGITS
     habitual
    0.27
    beits
    0.27
    _SL
    0.26
    éĢĤ
    0.25
     unary
    0.25
     rice
    0.25
    è¿Ļéĥ¨åĪĨ
    0.25
     dg
    0.24
     walkers
    0.24
    ja
    0.24
    Activations Density 1.776%

    No Known Activations