© 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. 23405
    Prev
    Next
    INDEX
    Explanations

    chr

    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
     heter
    -0.27
     killing
    -0.27
     Sark
    -0.25
    çĤĢ
    -0.25
    éķ¿å¤§
    -0.25
     lạc
    -0.25
    æļĹ示
    -0.25
     unloaded
    -0.24
    .await
    -0.24
    ro
    -0.24
    POSITIVE LOGITS
    atables
    0.30
    ?family
    0.29
     Dön
    0.28
    ä½ĵè´¨
    0.27
    ViewById
    0.27
    ifik
    0.26
    ationally
    0.26
    è¿ĩå¾Ĺ
    0.26
    ä¸Ĭåīį
    0.26
    .getInput
    0.26
    Activations Density 0.020%

    No Known Activations