© 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. 95763
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    embers
    -0.29
    alog
    -0.28
    ious
    -0.28
    ilitation
    -0.26
    endid
    -0.26
    ense
    -0.25
    çī¹æ®Ĭ
    -0.25
    pain
    -0.25
     slip
    -0.25
    flow
    -0.24
    POSITIVE LOGITS
     Heights
    0.33
     budgets
    0.30
    -muted
    0.28
    rowave
    0.27
     Tonight
    0.26
     heights
    0.25
    -budget
    0.25
    è¡·
    0.25
    Tonight
    0.25
    ç²®
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.