© 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. 56608
    Prev
    Next
    INDEX
    Explanations

    medical or code context

    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
    便ç§ĺ
    -0.30
     evolved
    -0.28
    INDER
    -0.25
    éĩį度
    -0.25
    çĸŁ
    -0.25
    .Documents
    -0.24
    ä¸Ń级
    -0.24
    ALS
    -0.24
     ves
    -0.24
    ymph
    -0.24
    POSITIVE LOGITS
    æįŁåĿı
    0.27
    ={({
    0.27
    çīĩ
    0.26
    disabled
    0.26
    AFF
    0.25
     HW
    0.25
    æ¯į
    0.25
    èĭ¦
    0.25
    minute
    0.25
     limp
    0.24
    Activations Density 0.001%

    No Known Activations