© 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. 65258
    Prev
    Next
    INDEX
    Explanations

    scanning algorithm concepts

    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
    apati
    -0.08
    åħ®
    -0.08
    /request
    -0.08
    Defined
    -0.08
    åħ¨å¥Ĺ
    -0.08
    æıĴä¸Ĭ
    -0.08
    orce
    -0.07
    quellen
    -0.07
    ouser
    -0.07
    okes
    -0.07
    POSITIVE LOGITS
    éĢIJ
    0.09
    éģįåİĨ
    0.09
    ç®Ĺæ³ķ
    0.09
     algorithm
    0.08
     scan
    0.07
    ç´¯
    0.07
     scanning
    0.07
     parcours
    0.07
     greedy
    0.07
     sorted
    0.07
    Activations Density 0.042%

    No Known Activations