© 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. 31-TRANSCODER-HP
    7. 18115
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨĻ
    -0.32
    bian
    -0.31
    bia
    -0.31
    writes
    -0.30
    éľ²
    -0.29
    ETA
    -0.28
    设æĸ½
    -0.26
    æĸĩæĺİ
    -0.26
    åĨĻä¸ĭ
    -0.26
    éģĵ
    -0.25
    POSITIVE LOGITS
     ÑģÑĤÑĢоки
    0.30
     flakes
    0.28
    æ²ı
    0.27
    CompleteListener
    0.26
    anzeigen
    0.26
    okes
    0.24
    ç¥ĵ
    0.24
    æīįè¡Į
    0.24
    ijk
    0.24
    finity
    0.24
    Activations Density 0.332%

    No Known Activations