© 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. 95927
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     math
    -0.30
    (math
    -0.27
    lop
    -0.27
    iton
    -0.27
    le
    -0.27
     disput
    -0.26
    .ISupportInitialize
    -0.26
     tet
    -0.26
     super
    -0.25
     Äijâu
    -0.25
    POSITIVE LOGITS
     Organisation
    0.31
    deaux
    0.31
     organising
    0.28
    worked
    0.26
    organisation
    0.26
    yw
    0.25
    åĽłèĢĮ
    0.25
    deen
    0.25
    çĻ½è¡£
    0.25
    sequent
    0.25
    Activations Density 0.016%

    No Known Activations