© 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. 4096
    Prev
    Next
    INDEX
    Explanations

    preparation and production

    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
     riman
    -0.08
    εÏģι
    -0.08
    _limits
    -0.08
    à¸Ńà¸ĩ
    -0.08
    ibase
    -0.08
    entered
    -0.08
    isional
    -0.08
    vore
    -0.08
     reordered
    -0.08
    åĶ±
    -0.08
    POSITIVE LOGITS
    æ³ķåĪ¶
    0.08
    ä¸įå¾Ĺå·²
    0.08
    åĪ¶å¤ĩ
    0.08
     purity
    0.07
    åĽºä½ĵ
    0.07
     dist
    0.07
     princip
    0.06
    åıªèĥ½çĶ¨
    0.06
    ä¸įèĥ½çĶ¨
    0.06
    _
    0.06
    Activations Density 0.002%

    No Known Activations