© 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. 40380
    Prev
    Next
    INDEX
    Explanations

    step by step instructions

    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
    çļĦä¸Ģç»Ħ
    -0.08
    ç»ıæŁ¥
    -0.07
    ãģķãģĦ
    -0.07
    Modes
    -0.07
    Ỽt
    -0.07
    onna
    -0.07
    lega
    -0.07
    egar
    -0.07
    ingan
    -0.07
    çļĦä¸ĢåįĬ
    -0.07
    POSITIVE LOGITS
    -step
    0.08
     step
    0.08
    ä¸ĢæŃ¥æŃ¥
    0.07
    step
    0.07
    ather
    0.07
    å¤§åľ£
    0.07
    éĢIJæŃ¥
    0.07
    ä¸Ģå¤ķ
    0.07
     steps
    0.06
     STEP
    0.06
    Activations Density 0.002%

    No Known Activations