© 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. 151428
    Prev
    Next
    INDEX
    Explanations

    attendance

    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
    raid
    -0.28
     getStatus
    -0.27
     objectType
    -0.25
    theses
    -0.25
     Reflex
    -0.24
    é£İæļ´
    -0.24
    ä¸ĥ大
    -0.24
    ainers
    -0.24
    akedown
    -0.24
     Sheridan
    -0.23
    POSITIVE LOGITS
    åī²
    0.26
    æ²»çIJĨ
    0.26
    .Comm
    0.25
    Ãły
    0.24
    '>{
    0.23
    æĬľ
    0.23
    æĪĮ
    0.23
     mult
    0.23
     torch
    0.23
     motor
    0.23
    Activations Density 0.376%

    No Known Activations