© 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. 149491
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     hott
    -0.27
    åĤ·
    -0.25
    累累
    -0.25
    ä¸Ģ人
    -0.25
    éĽ¾éľ¾
    -0.25
    antha
    -0.24
     Afterwards
    -0.24
    utherford
    -0.24
    ufacturer
    -0.24
     ims
    -0.24
    POSITIVE LOGITS
     recognition
    0.30
    rr
    0.27
     century
    0.27
     like
    0.26
     residential
    0.25
     km
    0.25
     most
    0.25
    å¹´åºķ
    0.25
    serviceName
    0.25
    樯
    0.25
    Activations Density 0.024%

    No Known Activations

    This feature has no known activations.