© 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. 30159
    Prev
    Next
    INDEX
    Explanations

    same size, reproduce results

    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
    æľªæ»¡
    -0.08
    -Jul
    -0.08
    åݦ
    -0.08
    è½®åĪ°
    -0.07
    深度åIJĪä½ľ
    -0.07
    çģ«å±±
    -0.07
     coopér
    -0.07
    soon
    -0.07
    æ·±éĢł
    -0.07
    èħ
    -0.07
    POSITIVE LOGITS
     sanity
    0.11
    _expected
    0.08
     expected
    0.08
     Sanity
    0.07
    ä¸Ŀä¸Ŀ
    0.07
    san
    0.07
    รั
    0.07
    San
    0.07
    qed
    0.07
    chal
    0.07
    Activations Density 0.012%

    No Known Activations