© 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. 27-TRANSCODER-HP
    7. 58269
    Prev
    Next
    INDEX
    Explanations

    documentation/regulations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raphic
    -0.29
    -controls
    -0.27
    æĭħä¿Ŀ
    -0.26
    ultimate
    -0.25
    wich
    -0.25
    éĥ¨ä»½
    -0.25
     saying
    -0.24
    secured
    -0.24
    éĥ¡
    -0.24
    казалоÑģÑĮ
    -0.24
    POSITIVE LOGITS
    å¼ĺ
    0.30
    éĺ¶æ®µ
    0.27
    潦
    0.27
    å¤§åľ°
    0.26
    indy
    0.26
     reopening
    0.25
    lings
    0.25
    èĤ¾èĦı
    0.25
    åįģåħ«æĿ¡
    0.24
    addle
    0.24
    Activations Density 0.002%

    No Known Activations