© 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. 109279
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    èĤī
    -0.28
    å°Ħ
    -0.27
    åį§
    -0.27
    æĸĻ
    -0.25
    bau
    -0.25
    heet
    -0.24
    roduction
    -0.24
    å¥Ī
    -0.24
    ç»´æĬ¤
    -0.24
    ainment
    -0.24
    POSITIVE LOGITS
     repro
    0.30
    ç»ıåķĨ
    0.28
     automatically
    0.27
    çªĹå¤ĸ
    0.26
     corrections
    0.26
    pherical
    0.25
     Conj
    0.25
     corrected
    0.25
     formally
    0.24
    é¹ľ
    0.24
    Activations Density 0.942%

    No Known Activations