© 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. 3625
    Prev
    Next
    INDEX
    Explanations

    operation of

    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
     Jair
    -0.07
     somew
    -0.06
    åİ»å®ĮæĪIJ
    -0.06
    åĩºèµ°
    -0.06
    æĢ§äº¤
    -0.06
    acqu
    -0.06
     maç
    -0.06
    üz
    -0.06
    èĪįå¾Ĺ
    -0.06
    è¾Ľéħ¸
    -0.06
    POSITIVE LOGITS
     appunto
    0.10
    entes
    0.09
     Reese
    0.08
    èĶ»
    0.08
    /proto
    0.07
    éĤ£é¢Ĺ
    0.07
    izr
    0.07
    ENTES
    0.07
    éĤ¦
    0.07
    ç¿°
    0.07
    Activations Density 0.908%

    No Known Activations