© 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. 149449
    Prev
    Next
    INDEX
    Explanations

    this or that

    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
    sert
    -0.30
    å²ģ
    -0.27
    urile
    -0.26
     imper
    -0.25
    sworth
    -0.25
    pent
    -0.25
    空åīį
    -0.24
    eten
    -0.24
    etros
    -0.24
    æįŁ
    -0.24
    POSITIVE LOGITS
     since
    0.29
     (âĪ
    0.28
    éĢĻ樣
    0.28
     Ballard
    0.27
     ÑĤакие
    0.26
    æ¯ĶèµĽä¸Ń
    0.26
     despite
    0.26
    ç»Ļ大家
    0.26
    .Setup
    0.25
     so
    0.24
    Activations Density 0.935%

    No Known Activations