© 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. 151102
    Prev
    Next
    INDEX
    Explanations

    the/a

    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
    icit
    -0.27
    ä»İ容
    -0.27
    æĬ¥å¤į
    -0.27
     Beitrag
    -0.26
    took
    -0.26
    åĿĽ
    -0.26
    åĽŀåIJĪ
    -0.25
     heck
    -0.25
    tribution
    -0.25
    æŀģ端
    -0.25
    POSITIVE LOGITS
    istar
    0.25
     dispersion
    0.24
    ç½ijé¦ĸ页
    0.24
    oval
    0.24
    丫
    0.24
    antro
    0.23
    anje
    0.23
    udas
    0.23
    æĹ©é¤IJ
    0.23
     treated
    0.23
    Activations Density 0.008%

    No Known Activations