© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18784
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itten
    -0.08
    ité
    -0.07
    achen
    -0.06
    avax
    -0.06
    ç¥ĸåħĪ
    -0.06
    пÑĭ
    -0.06
     $$$
    -0.06
    athers
    -0.06
    .setter
    -0.06
    läss
    -0.06
    POSITIVE LOGITS
    ...",
    0.08
    !",
    0.08
    unca
    0.07
    lsa
    0.07
    atel
    0.07
    orney
    0.07
    _HIGH
    0.07
     ?",
    0.07
    人影
    0.06
    !',
    0.06
    Activations Density 0.583%

    No Known Activations