© 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. 149465
    Prev
    Next
    INDEX
    Explanations

    call

    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
    æŃ£å¥½
    -0.28
    istry
    -0.26
    unication
    -0.25
    -Mart
    -0.25
    udio
    -0.25
    è¦ģæľī
    -0.25
    ernity
    -0.25
    zier
    -0.24
    andard
    -0.24
    unj
    -0.23
    POSITIVE LOGITS
    è¿Ļåıª
    0.28
    è¿Ļ款车
    0.28
    è¿ĻåIJį
    0.28
    该项
    0.28
    æŃ¤é¡¹
    0.28
    è¿Ļç§į
    0.27
    è¿Ļ项
    0.27
    è¿ĻåĿĹ
    0.26
     this
    0.26
    åIJįä¹ī
    0.26
    Activations Density 0.032%

    No Known Activations