© 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. 96199
    Prev
    Next
    INDEX
    Explanations

    Technical or formal writing

    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
     dire
    -0.28
     ded
    -0.27
     disrupted
    -0.27
    YTE
    -0.26
    dire
    -0.26
     disruption
    -0.25
    asin
    -0.25
     achieved
    -0.25
     reversal
    -0.25
    认åIJĮ
    -0.25
    POSITIVE LOGITS
    loader
    0.30
    æĦı
    0.27
     Panc
    0.27
     Employees
    0.27
    GPL
    0.27
     Gener
    0.26
    åIJ¡
    0.26
    еÑĩен
    0.26
    ä¸ĢæŃ¥
    0.26
    iley
    0.25
    Activations Density 0.103%

    No Known Activations