© 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. 22957
    Prev
    Next
    INDEX
    Explanations

    Random text and numbers

    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
    æĸ°å¼Ģ
    -0.28
    ocate
    -0.27
    åij¢
    -0.27
    çīĩåŃIJ
    -0.26
    éĺµåľ°
    -0.26
    åĵģå¾·
    -0.26
    æ¯ĶèµĽ
    -0.25
    ivate
    -0.25
    媳
    -0.25
    çļĦè¯Ŀ
    -0.25
    POSITIVE LOGITS
    纲
    0.29
    ç»´å¥ĩ
    0.25
    DataContext
    0.25
    aÄŁ
    0.25
    èľĤ
    0.25
    pike
    0.25
    eut
    0.24
    :list
    0.24
    è¯Ĥ
    0.24
    ueur
    0.24
    Activations Density 0.000%

    No Known Activations