© 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. 95576
    Prev
    Next
    INDEX
    Explanations

    Premature / Term births

    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
    аниÑİ
    -0.29
     Mercy
    -0.29
    |[
    -0.26
    _maker
    -0.25
     blues
    -0.25
    lean
    -0.25
     tấm
    -0.24
    é¢Ĩçķ¥
    -0.24
    earth
    -0.24
    oose
    -0.24
    POSITIVE LOGITS
     Prem
    0.54
    足
    0.53
    Prem
    0.50
     prem
    0.49
     premature
    0.47
     term
    0.40
    term
    0.38
     prematurely
    0.38
    åīįç½®
    0.37
    Term
    0.36
    Activations Density 1.281%

    No Known Activations