© 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. 96050
    Prev
    Next
    INDEX
    Explanations

    Universities

    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
    utra
    -0.30
    uParam
    -0.27
    agram
    -0.27
    åĮĸ解
    -0.26
    uates
    -0.26
    庵
    -0.26
    æµģåĬ¨
    -0.25
    rts
    -0.24
     NSK
    -0.24
     Millennium
    -0.24
    POSITIVE LOGITS
    è¾Ł
    0.30
     now
    0.28
    .ng
    0.25
     maintenant
    0.25
    çİ°åľ¨
    0.25
    exc
    0.24
    é¦IJ
    0.24
    è¿ij代
    0.23
    cour
    0.23
    election
    0.23
    Activations Density 0.888%

    No Known Activations