© 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. 108917
    Prev
    Next
    INDEX
    Explanations

    L

    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
    è°
    -0.28
    odem
    -0.27
    missive
    -0.26
    综åIJĪæ²»çIJĨ
    -0.25
    hawks
    -0.25
    ¬¸
    -0.24
    panse
    -0.24
     compromise
    -0.24
    hec
    -0.23
     bic
    -0.23
    POSITIVE LOGITS
    ar
    0.27
    æ³Ĺ
    0.27
    $',
    0.27
    ir
    0.26
    ittings
    0.25
    åį«
    0.25
    çļĦçIJĨ解
    0.25
    Est
    0.25
    ${
    0.25
    judge
    0.25
    Activations Density 0.145%

    No Known Activations