© 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. 96086
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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
    dated
    -0.24
    less
    -0.23
    igen
    -0.23
     ur
    -0.23
    serir
    -0.23
    .removeFrom
    -0.23
    棵æłij
    -0.23
    compet
    -0.22
    LESS
    -0.22
    åĨĻçĿĢ
    -0.22
    POSITIVE LOGITS
    åIJĮç±»
    0.30
    orks
    0.29
    RIES
    0.28
    模
    0.26
    lu
    0.26
    æģŃåĸľ
    0.26
    ä¾ĭå¤ĸ
    0.26
    xFC
    0.25
     ventil
    0.25
     Crane
    0.24
    Activations Density 0.882%

    No Known Activations