© 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. 18401
    Prev
    Next
    INDEX
    Explanations

    strike or hit

    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
    ieux
    -0.08
    zus
    -0.07
    atics
    -0.07
    abri
    -0.07
    ear
    -0.07
    eming
    -0.07
    Ĩµ
    -0.07
    arning
    -0.07
    дко
    -0.07
    coni
    -0.07
    POSITIVE LOGITS
    æĵĬ
    0.11
    æĴĥ
    0.10
    aylor
    0.08
    åĩ»
    0.08
    éŁ¿
    0.08
    æĬ½æŁ¥æ£ĢæŁ¥
    0.07
    è¦ģ害
    0.07
     frapp
    0.07
    声ä¸Ń
    0.07
    DOWN
    0.07
    Activations Density 0.126%

    No Known Activations