© 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. 51770
    Prev
    Next
    INDEX
    Explanations

    two molecules or units

    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
    Speak
    -0.08
    ä¸įç»Ļ
    -0.08
    éton
    -0.08
    ä¸Ģè·¯
    -0.07
     bulls
    -0.07
    ombs
    -0.07
    isca
    -0.07
    uline
    -0.07
    åľ
    -0.07
    æ¢Ń
    -0.07
    POSITIVE LOGITS
     identical
    0.09
    éĩįå¤į
    0.08
    缸éĤ»
    0.08
    å¤įåĪ¶
    0.08
     repetition
    0.08
    è¤ĩ製
    0.07
     clone
    0.07
     symmetry
    0.07
     replication
    0.07
    å®ŀä¾ĭ
    0.07
    Activations Density 0.070%

    No Known Activations