© 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. 151054
    Prev
    Next
    INDEX
    Explanations

    journals

    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
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ĻæĿ¡
    -0.29
    Cons
    -0.25
     Thread
    -0.25
    allet
    -0.25
     Threads
    -0.25
    åħĭ
    -0.24
     Cons
    -0.24
    .links
    -0.24
    ral
    -0.24
     inici
    -0.24
    POSITIVE LOGITS
     journals
    0.31
    jid
    0.30
    å¥
    0.29
    publish
    0.29
     journal
    0.29
     Publishers
    0.28
     submissions
    0.28
    åѦä¼ļ
    0.26
    InnerText
    0.26
     spreading
    0.26
    Activations Density 0.883%

    No Known Activations