© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96354
    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_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     composition
    -1.79
     Composition
    -1.63
     compositions
    -1.59
    ç»ĦæĪIJ
    -1.58
    Composition
    -1.52
    composition
    -1.49
     compos
    -1.38
     ÑģоÑģÑĤав
    -1.33
     compose
    -1.33
     composing
    -1.25
    POSITIVE LOGITS
    ä¼ī
    0.25
    ONES
    0.25
    åħ´æĹº
    0.24
     Syndrome
    0.23
    éĵ¨
    0.23
    èµ°å¾Ĺ
    0.23
    esen
    0.23
    æİ¥å¾ħ
    0.23
    ongs
    0.23
    rud
    0.23
    Activations Density 0.890%

    No Known Activations