© 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. 35-TRANSCODER-HP
    7. 39633
    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_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Radical
    -0.32
     radical
    -0.31
    .rad
    -0.30
     radicals
    -0.29
     rad
    -0.29
    æ¯ıä¸Ģ个
    -0.28
     radix
    -0.28
     facts
    -0.27
     RAD
    -0.27
    æ¦Ĥ
    -0.26
    POSITIVE LOGITS
    AYS
    0.41
    ays
    0.33
    aying
    0.33
    ayo
    0.33
    AY
    0.33
    ay
    0.33
    ayed
    0.32
    Ay
    0.30
    ains
    0.30
     Ay
    0.29
    Activations Density 0.131%

    No Known Activations