© 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. 19673
    Prev
    Next
    INDEX
    Explanations

    Different languages and cultures

    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
    lobber
    -0.26
     contracted
    -0.25
    LEM
    -0.25
    ('*',
    -0.25
    鼶
    -0.25
     SCRIPT
    -0.25
    ÑĤиÑĢ
    -0.25
    TD
    -0.25
    enkins
    -0.25
    ays
    -0.25
    POSITIVE LOGITS
    éĴ¹
    0.27
    abay
    0.27
    atra
    0.26
    èĩĤ
    0.26
     Ansi
    0.26
    å·¾
    0.25
     numeric
    0.25
    uster
    0.25
    orca
    0.25
    ä¾
    0.24
    Activations Density 0.092%

    No Known Activations