© 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. 56638
    Prev
    Next
    INDEX
    Explanations

    product brands or named entities

    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
    æ®Ĭ
    -0.07
    æį¢
    -0.07
    icule
    -0.07
    çĴŁ
    -0.06
    è¾°
    -0.06
     homog
    -0.06
    éľĨ
    -0.06
    ç»Ħå§Ķä¼ļ
    -0.06
     Cog
    -0.06
    çŁ
    -0.06
    POSITIVE LOGITS
    -like
    0.08
    -compatible
    0.08
    -related
    0.08
    -type
    0.08
    -style
    0.07
    unner
    0.07
    人æĿ¥è¯´
    0.07
    -derived
    0.07
    人åİ»
    0.07
    -era
    0.07
    Activations Density 0.919%

    No Known Activations