© 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. 19674
    Prev
    Next
    INDEX
    Explanations

    lexical semantics

    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
     dies
    -0.29
    die
    -0.28
    ç¢ĺ
    -0.27
     prelim
    -0.26
    airy
    -0.26
    icator
    -0.26
    mare
    -0.25
     DIE
    -0.25
    udeau
    -0.25
     die
    -0.24
    POSITIVE LOGITS
    aton
    0.32
    椿
    0.29
    æ£ł
    0.28
    <::
    0.28
    oton
    0.26
     tang
    0.25
    å¾Ĵ
    0.25
    peat
    0.25
    çĪ±äºº
    0.24
    æijĨ
    0.24
    Activations Density 0.940%

    No Known Activations