© 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. 25-TRANSCODER-HP
    7. 107683
    Prev
    Next
    INDEX
    Explanations

    Code/import statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alone
    -0.28
    alone
    -0.28
    -alone
    -0.27
    erk
    -0.26
     DY
    -0.26
    eros
    -0.26
     pier
    -0.26
    BI
    -0.25
    abble
    -0.25
    æľīçĶ¨çļĦ
    -0.25
    POSITIVE LOGITS
    _escape
    0.29
    Escape
    0.27
    arris
    0.27
    enance
    0.27
     Vân
    0.25
    æ©IJ
    0.25
     Nguy
    0.25
    :id
    0.25
    åIJİæİĴ
    0.24
    åŀ
    0.24
    Activations Density 0.129%

    No Known Activations