© 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. 109384
    Prev
    Next
    INDEX
    Explanations

    single digit numbers

    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
    bra
    -0.26
    variants
    -0.24
    çIJĨ解åĴĮ
    -0.24
    足
    -0.24
    _|
    -0.23
    ç²ī
    -0.23
    XS
    -0.23
    ilon
    -0.23
     EU
    -0.23
    REA
    -0.23
    POSITIVE LOGITS
    è´µ
    0.26
    éĶ¦æłĩ
    0.25
     Means
    0.25
    ä¸ĩæĪ·
    0.25
     Module
    0.24
    ç§ĺ书
    0.24
     inv
    0.24
     disappears
    0.24
     Plug
    0.23
    å¼ĩ
    0.23
    Activations Density 0.025%

    No Known Activations