© 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. 31-TRANSCODER-HP
    7. 17909
    Prev
    Next
    INDEX
    Explanations

    radiation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Languages
    -0.31
    JOR
    -0.30
    éķ¿å¤§äºĨ
    -0.29
    å¾Ĵ
    -0.29
    jie
    -0.28
    gere
    -0.27
    sav
    -0.27
    ements
    -0.24
    Favorites
    -0.24
    èĩªèº«
    -0.24
    POSITIVE LOGITS
     emission
    0.36
    field
    0.32
     emiss
    0.32
     field
    0.32
     emissions
    0.29
     emitted
    0.28
     emitting
    0.28
     emits
    0.27
     source
    0.27
     damage
    0.27
    Activations Density 0.024%

    No Known Activations