© 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. 22562
    Prev
    Next
    INDEX
    Explanations

    water

    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
     Hunts
    -0.26
    æĥ
    -0.26
    insky
    -0.26
    aviolet
    -0.26
    åħįéĻ¤
    -0.26
    ç¼Ł
    -0.26
    starter
    -0.25
    grown
    -0.25
    ä¸īæľŁ
    -0.24
     toll
    -0.24
    POSITIVE LOGITS
     Accred
    0.28
     Writers
    0.27
    rats
    0.27
    jam
    0.27
    RAR
    0.25
    imo
    0.25
    Ranked
    0.25
    Circular
    0.25
     Público
    0.25
     barrel
    0.24
    Activations Density 0.001%

    No Known Activations