© 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. 149148
    Prev
    Next
    INDEX
    Explanations

    some

    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
     toward
    -0.30
     as
    -0.28
     Fri
    -0.27
    ä¸Ģ座
    -0.27
    -Co
    -0.27
     during
    -0.26
    ors
    -0.26
    at
    -0.26
    -co
    -0.26
    ·æĸ°
    -0.25
    POSITIVE LOGITS
    imits
    0.32
    èĢģ人家
    0.30
    hog
    0.30
    VRT
    0.29
    pez
    0.27
    gio
    0.26
     UserDetails
    0.26
    eous
    0.26
     informations
    0.26
    æ±ŁåĮº
    0.26
    Activations Density 0.208%

    No Known Activations