Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 8068
    Prev
    Next
    INDEX
    Explanations

    Present tense "to be"

    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
    åĥµ
    -0.28
     WELL
    -0.28
    äºķ
    -0.28
    æĪĽ
    -0.26
    æĿŁ
    -0.26
    cznÄħ
    -0.26
    èĢĮæĪIJ
    -0.25
     well
    -0.25
    åѤ
    -0.24
    missive
    -0.24
    POSITIVE LOGITS
    ilst
    0.27
    idency
    0.25
    íıŃ
    0.25
    chs
    0.25
    obox
    0.25
    ucs
    0.25
    ç¥
    0.25
     tod
    0.24
    oes
    0.24
    Fal
    0.24
    Activations Density 0.074%

    No Known Activations