© 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. 30-TRANSCODER-HP
    7. 95481
    Prev
    Next
    INDEX
    Explanations

    Blo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nte
    -0.29
    nder
    -0.27
    خت
    -0.27
    icture
    -0.27
    Round
    -0.26
    (round
    -0.26
    xis
    -0.25
    èĥ½åľ¨
    -0.25
    _round
    -0.25
    è°Ľ
    -0.25
    POSITIVE LOGITS
    otch
    0.29
    è¿Ľç¨ĭ
    0.27
     ember
    0.27
    chains
    0.26
    eman
    0.25
    azel
    0.25
    龸
    0.24
    èī³
    0.24
    æĹ¢
    0.24
    azo
    0.24
    Activations Density 0.885%

    No Known Activations