© 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. 31-TRANSCODER-HP
    7. 19672
    Prev
    Next
    INDEX
    Explanations

    flooring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æłij
    -0.29
    ục
    -0.29
    å¹ķåIJİ
    -0.27
    ken
    -0.26
     trees
    -0.25
    unit
    -0.25
    iedades
    -0.25
    æľīæķĪæĢ§
    -0.25
    tree
    -0.25
     shells
    -0.25
    POSITIVE LOGITS
    vig
    0.29
    Mart
    0.28
    竦
    0.26
    ddy
    0.25
     Straw
    0.25
    ateg
    0.25
    akah
    0.25
    çµIJæ§ĭ
    0.25
    ãģĻ
    0.25
    ç»ĵæŀĦè°ĥæķ´
    0.24
    Activations Density 1.586%

    No Known Activations