© 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. 95296
    Prev
    Next
    INDEX
    Explanations

    amount

    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
    gaard
    -0.28
    udu
    -0.27
    æĪIJåĵģ
    -0.25
    qv
    -0.25
    QUIRED
    -0.24
    quired
    -0.24
    CADE
    -0.24
    ingham
    -0.23
    ashboard
    -0.23
    QUAL
    -0.23
    POSITIVE LOGITS
     amount
    1.46
    amount
    1.37
     amounts
    1.26
    Amount
    1.25
     Amount
    1.23
    _amount
    1.20
    .amount
    1.15
    (amount
    1.07
    éĩijé¢Ŀ
    1.05
    .Amount
    0.95
    Activations Density 1.018%

    No Known Activations