© 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. 25-TRANSCODER-HP
    7. 107282
    Prev
    Next
    INDEX
    Explanations

    say "question"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -lib
    -0.26
    libraries
    -0.26
     Exact
    -0.25
    æ¢ĥ
    -0.25
    ç¥ī
    -0.24
    IndexChanged
    -0.24
     midfield
    -0.24
    estone
    -0.24
    empt
    -0.24
    mor
    -0.24
    POSITIVE LOGITS
    еÑģ
    0.28
    tml
    0.27
    ä¹İ
    0.27
    Äĩ
    0.25
    gba
    0.24
     Gä
    0.24
    ç¼ĺ
    0.24
    =device
    0.24
    æĪIJ
    0.24
    uality
    0.24
    Activations Density 1.012%

    No Known Activations