© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    nearby locations or neighbors

    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
    ä½łçļĦåIJįåŃĹ
    -0.07
    ç¯ĩå¹ħ
    -0.07
     acom
    -0.07
    纵
    -0.07
    ahoo
    -0.07
    unki
    -0.07
    ä»İåı¤
    -0.07
    èĢ¸
    -0.07
    Interop
    -0.06
     allocation
    -0.06
    POSITIVE LOGITS
     surrounding
    0.10
    åij¨åĽ´
    0.09
    éĤ»å±ħ
    0.09
     Surround
    0.09
     neighbors
    0.08
     surroundings
    0.08
     neighbours
    0.08
    åij¨åĽ²
    0.08
     surrounds
    0.08
     neighboring
    0.08
    Activations Density 0.004%

    No Known Activations