© 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. 32-TRANSCODER-HP
    7. 43394
    Prev
    Next
    INDEX
    Explanations

    trans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eer
    -0.32
    feit
    -0.30
    неÑĢ
    -0.28
    ertext
    -0.28
    asia
    -0.26
     ASC
    -0.26
     supp
    -0.26
    agara
    -0.25
    æľįåĬ¡æ°´å¹³
    -0.25
    lected
    -0.25
    POSITIVE LOGITS
    ce
    0.29
    iv
    0.27
    lij
    0.26
    åľī
    0.25
     failing
    0.25
    li
    0.25
    ·¨
    0.25
    ailing
    0.25
    æµ®
    0.24
    ç¼ĸåĨĻ
    0.24
    Activations Density 0.002%

    No Known Activations