© 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. 58046
    Prev
    Next
    INDEX
    Explanations

    mods, amp, keg, shoot

    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
    ↵
    -0.08
     reconstruct
    -0.06
     therein
    -0.06
    IBM
    -0.06
     Born
    -0.06
    ODE
    -0.06
     categor
    -0.06
    æ´ŀå¯Ł
    -0.06
    CNN
    -0.06
     undergoing
    -0.06
    POSITIVE LOGITS
     aftermarket
    0.09
    å®ŀæµĭ
    0.09
     Amateur
    0.08
     recomend
    0.08
    ç§ĭæľĪ
    0.08
    æݨèįIJçļĦ
    0.08
     hobby
    0.08
    -loader
    0.08
    æ¯Ķä½ł
    0.08
     amatör
    0.08
    Activations Density 0.205%

    No Known Activations