© 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. 29746
    Prev
    Next
    INDEX
    Explanations

    medicine

    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
    解æķ£
    -0.28
     Kön
    -0.27
    åıĺæĽ´
    -0.26
     defaultCenter
    -0.25
    èģļ
    -0.25
    isper
    -0.25
    exampleInput
    -0.25
    cheap
    -0.24
    ç´«
    -0.24
    ç³Ĭ
    -0.24
    POSITIVE LOGITS
    berg
    0.28
    arat
    0.28
    esto
    0.27
    为代表
    0.27
    mite
    0.27
     Ñģобой
    0.26
    arto
    0.25
    icode
    0.25
     future
    0.25
    comed
    0.25
    Activations Density 0.256%

    No Known Activations