© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95268
    Prev
    Next
    INDEX
    Explanations

    research and evidence

    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
    uÅŁ
    -0.30
    缸åħ³åĨħ容
    -0.26
     fort
    -0.26
     neatly
    -0.25
    ä¸ĢéĿ¢
    -0.24
    Patch
    -0.24
    odb
    -0.24
    iais
    -0.23
     forcibly
    -0.23
    spar
    -0.23
    POSITIVE LOGITS
     evidence
    0.43
     liter
    0.35
    è¯ģæį®
    0.34
     Evidence
    0.34
    Evidence
    0.33
     work
    0.31
     literature
    0.30
    liter
    0.28
    æĹ©æĻļ
    0.28
     research
    0.27
    Activations Density 0.891%

    No Known Activations