© 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. 151396
    Prev
    Next
    INDEX
    Explanations

    scientific research methods

    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
    æĦŁ
    -0.31
    åĬ³åĬ¨èĢħ
    -0.27
     Variety
    -0.27
    æĤĮ
    -0.27
     Book
    -0.26
    bolt
    -0.26
    åıĮ
    -0.25
     indoors
    -0.25
    èĨĢ
    -0.25
    å¹´ä¸ĭåįĬå¹´
    -0.24
    POSITIVE LOGITS
     either
    0.38
    either
    0.33
     expensive
    0.29
     costly
    0.28
    çĻ½èī²çļĦ
    0.28
    }}{{
    0.27
     titular
    0.27
    ifetime
    0.27
     passive
    0.27
    Either
    0.27
    Activations Density 0.907%

    No Known Activations