© 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. 106975
    Prev
    Next
    INDEX
    Explanations

    code/filepaths

    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
    Negative Logits
    .shtml
    -0.27
    ä¿¡ä»»
    -0.27
    alis
    -0.25
     Folding
    -0.25
    umblr
    -0.24
    åī§ä¸Ń
    -0.24
    éĤ£éĩĮ
    -0.24
    ек
    -0.24
    æĴ¤
    -0.23
    ä»İå°ı
    -0.23
    POSITIVE LOGITS
    æįī
    0.27
    åݻ买
    0.25
    roid
    0.25
     ?",
    0.24
    spin
    0.24
    herit
    0.24
    èĩªåľ¨
    0.23
    æĬĬè¿Ļ个
    0.23
     ?,
    0.23
     fallback
    0.23
    Activations Density 0.053%

    No Known Activations