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. 163259
    Prev
    Next
    INDEX
    Explanations

    Programming and low-level computing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auc
    -0.27
    CALL
    -0.25
    META
    -0.23
    VEST
    -0.23
    å°¼äºļ
    -0.23
    cou
    -0.23
     ÄIJông
    -0.23
     Essays
    -0.23
     Volunteer
    -0.23
    _call
    -0.23
    POSITIVE LOGITS
    -wise
    0.30
    Locator
    0.28
    çķĻç»Ļ
    0.27
    -like
    0.27
    adic
    0.27
    æļĤ
    0.26
    -separated
    0.26
    çķ´
    0.25
     residue
    0.25
    -wide
    0.25
    Activations Density 0.009%

    No Known Activations