© 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. 3763
    Prev
    Next
    INDEX
    Explanations

    sequence or list items

    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
    eliac
    -0.07
    itan
    -0.06
     embar
    -0.06
    riott
    -0.06
     chapter
    -0.06
    æľ¬å¸ĸ
    -0.06
    _pref
    -0.06
    è¿ľæ¯Ķ
    -0.06
    orpion
    -0.06
    æºIJçļĦ
    -0.06
    POSITIVE LOGITS
    AtPath
    0.08
    isable
    0.08
    asses
    0.08
     maths
    0.07
    ä¹IJä¹İ
    0.07
    æľºä¸Ĭ
    0.07
    ASM
    0.07
    èīºæľ¯ä¸Ńå¿ĥ
    0.07
    æ²³éĩĮ
    0.07
    éĢ¾æľŁæľª
    0.07
    Activations Density 0.001%

    No Known Activations