© 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. 32-TRANSCODER-HP
    7. 41173
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
    iment
    -0.33
    ames
    -0.32
    apers
    -0.28
    ading
    -0.28
    mes
    -0.27
    æĥħ
    -0.27
    åĿĢ
    -0.26
     pap
    -0.26
     BASIS
    -0.25
    çī©
    -0.25
    POSITIVE LOGITS
     act
    0.31
     acts
    0.28
    	act
    0.28
     elbows
    0.26
    еле
    0.26
    宵
    0.26
     acted
    0.26
     Act
    0.25
    Localized
    0.25
     Shr
    0.25
    Activations Density 0.006%

    No Known Activations