© 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. 23319
    Prev
    Next
    INDEX
    Explanations

    Code and finance

    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
     floor
    -0.25
    ÃŃt
    -0.25
    ianne
    -0.25
    rooms
    -0.25
    sessions
    -0.24
    æĴŃ
    -0.24
     Lun
    -0.24
    .prepend
    -0.24
     Cit
    -0.23
    ceil
    -0.23
    POSITIVE LOGITS
    imon
    0.28
    庶
    0.27
     ServiceException
    0.25
     dh
    0.25
    ypes
    0.24
    dni
    0.24
    issement
    0.24
     Dani
    0.24
    第ä¸ĢæĿ¡
    0.23
    âīĥ
    0.23
    Activations Density 0.002%

    No Known Activations