© 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. 24-TRANSCODER-HP
    7. 149283
    Prev
    Next
    INDEX
    Explanations

    what

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     how
    -0.27
    å½±åĵįåĬĽçļĦ
    -0.26
    faf
    -0.25
     straw
    -0.24
     logic
    -0.24
     Matching
    -0.24
     Facing
    -0.24
    éĿ¢ä¸´çļĦ
    -0.24
    ist
    -0.23
    /rand
    -0.23
    POSITIVE LOGITS
    odic
    0.26
    åīģ
    0.26
    åĩºæĿ¥
    0.25
    odia
    0.25
     PROGMEM
    0.24
    odom
    0.23
     unfolded
    0.23
    -meter
    0.23
     Bru
    0.23
    ioned
    0.23
    Activations Density 0.139%

    No Known Activations