© 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. 39764
    Prev
    Next
    INDEX
    Explanations

    Paragraphs of text

    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
    -INF
    -0.29
    mite
    -0.26
    anders
    -0.24
    éĻ¢
    -0.24
    å°¼äºļ
    -0.24
    è¿ĩåİ»
    -0.24
    oron
    -0.23
    让人们
    -0.23
     Phil
    -0.23
    说èĩªå·±
    -0.23
    POSITIVE LOGITS
    æĹ»
    0.30
    OUCH
    0.30
    æ°´éĩı
    0.25
    衾
    0.25
    htag
    0.25
     epub
    0.25
    ä¸įåı¯èĥ½
    0.25
    åģļå®Į
    0.24
    .ua
    0.24
    çīĪæĿĥå½Ĵ
    0.24
    Activations Density 0.062%

    No Known Activations