© 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. 14-TRANSCODER-HP
    7. 39754
    Prev
    Next
    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snap
    -0.30
    Snap
    -0.29
    è®°èĢħ
    -0.27
    åĨį说
    -0.26
    atable
    -0.26
     invol
    -0.26
    аÑİÑĤÑģÑı
    -0.25
    adier
    -0.25
    Fun
    -0.25
    _snap
    -0.25
    POSITIVE LOGITS
    geme
    0.31
    weise
    0.28
    orm
    0.26
    washer
    0.25
     tog
    0.24
    ushing
    0.24
    .sendStatus
    0.24
     homepage
    0.24
    é»ĺé»ĺ
    0.23
    ailing
    0.23
    Activations Density 2.563%

    No Known Activations