© 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. 107042
    Prev
    Next
    INDEX
    Explanations

    non-English/technical text

    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
    ield
    -0.40
    icial
    -0.37
    usion
    -0.36
    ields
    -0.33
    riends
    -0.33
    ayette
    -0.33
    icient
    -0.33
    ramework
    -0.32
    ord
    -0.32
    loat
    -0.32
    POSITIVE LOGITS
    fu
    0.31
    夫
    0.30
    aled
    0.28
    flo
    0.27
    fan
    0.26
    atives
    0.26
    far
    0.26
    kor
    0.26
     thôi
    0.25
     ret
    0.25
    Activations Density 0.660%

    No Known Activations