© 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. 23132
    Prev
    Next
    INDEX
    Explanations

    state

    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
    æĹ¥èµ·
    -0.28
    WS
    -0.27
    LU
    -0.27
    ç¿¥
    -0.27
    çĸı
    -0.26
    DS
    -0.26
    å·¢
    -0.26
    ;element
    -0.25
    人äºĭ
    -0.25
    亹
    -0.25
    POSITIVE LOGITS
    éĩįéĩį
    0.29
    çģ¯çģ«
    0.28
     Rica
    0.27
     sec
    0.26
    .nlm
    0.26
    è¡£
    0.26
    quia
    0.26
     mie
    0.25
    /sec
    0.25
    >Edit
    0.25
    Activations Density 0.010%

    No Known Activations