© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14631
    Prev
    Next
    INDEX
    Explanations

    Roman numerals or numbers followed by 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
    atto
    -0.07
    olato
    -0.07
    究
    -0.07
    ാര
    -0.07
    á»ij
    -0.07
    ahari
    -0.06
    arang
    -0.06
    riften
    -0.06
    渴
    -0.06
    RelativeTo
    -0.06
    POSITIVE LOGITS
    less
    0.07
    äºİä¸Ģ
    0.07
    коÑĤ
    0.07
    bower
    0.07
    éĤ£çīĩ
    0.07
    llum
    0.07
    eds
    0.06
    (SS
    0.06
    ÑĹ
    0.06
    zzo
    0.06
    Activations Density 0.420%

    No Known Activations