© 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. 22-TRANSCODER-HP
    7. 87683
    Prev
    Next
    INDEX
    Explanations

    Traffic accidents and injuries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıįé¦Ī
    -0.33
     feedback
    -0.29
    æĺİç¡®
    -0.27
     ë©
    -0.26
     Ber
    -0.26
    ?option
    -0.26
    ocol
    -0.25
    è¡¥åħħ
    -0.25
    -feedback
    -0.25
    oppel
    -0.25
    POSITIVE LOGITS
    é£Ĵ
    0.27
    AGR
    0.27
    fat
    0.26
     unprotected
    0.26
    æĢ§åij½
    0.26
    GORITHM
    0.25
    verage
    0.25
    lef
    0.25
    çĨĻ
    0.24
    aur
    0.24
    Activations Density 0.015%

    No Known Activations