© 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. 94931
    Prev
    Next
    INDEX
    Explanations

    risk

    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
    Negative Logits
    .stem
    -0.32
    éĶı
    -0.30
    pector
    -0.28
    .Entry
    -0.27
     Walton
    -0.26
    elf
    -0.26
    å®Įåħ¨æ²¡æľī
    -0.25
    .setAuto
    -0.25
     Stra
    -0.25
     undercut
    -0.25
    POSITIVE LOGITS
     risk
    0.68
    é£İéĻ©
    0.68
     risks
    0.62
    èĥĨ
    0.60
    çļĦé£İéĻ©
    0.60
     Risk
    0.59
    Risk
    0.56
    risk
    0.56
    -risk
    0.56
    風éļª
    0.52
    Activations Density 0.883%

    No Known Activations