© 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. 16739
    Prev
    Next
    INDEX
    Explanations

    monitors and tinnitus

    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
    ritis
    -0.07
    StateManager
    -0.07
    _argv
    -0.07
    移åĬ¨çīĪ
    -0.07
    çķĻä½ı
    -0.07
    \\.
    -0.06
    agher
    -0.06
    illus
    -0.06
    æīĢå±ŀåĪĨç±»
    -0.06
    !.
    -0.06
    POSITIVE LOGITS
    opus
    0.08
     opr
    0.08
    ç¾İéħĴ
    0.07
    ffic
    0.07
    èµĮ
    0.07
    æĹłåıĮ
    0.07
    POSE
    0.07
    æĻ®åĪ©
    0.07
    ff
    0.07
    iri
    0.06
    Activations Density 0.016%

    No Known Activations