© 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. 23-TRANSCODER-HP
    7. 24653
    Prev
    Next
    INDEX
    Explanations

    conjunctions and commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htags
    -0.28
    лоÑĤ
    -0.27
    ãģĹãģŁãĤĤãģ®
    -0.26
    次
    -0.26
    -cigarettes
    -0.24
    ãģ¤ãģĦ
    -0.24
    ashes
    -0.24
     Tüm
    -0.24
    ments
    -0.24
    æĩ·
    -0.24
    POSITIVE LOGITS
    éķ¿çĽ¸
    0.27
    åijIJ
    0.26
    读书
    0.25
    å¸ĤæĶ¿åįı
    0.25
    æľ
    0.25
     ÑĢÑĭ
    0.24
    ä¿Ħ
    0.24
    ç»ıéªĮ
    0.24
    agr
    0.23
     knowledgeable
    0.23
    Activations Density 0.005%

    No Known Activations