© 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. 51617
    Prev
    Next
    INDEX
    Explanations

    difference or implication

    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
    å¼Ģå±ķ好
    -0.08
    ForResult
    -0.07
    iva
    -0.07
    æ¸ħæ³ī
    -0.07
    .bz
    -0.07
    éľĵ
    -0.07
    å°±çŁ¥éģĵ
    -0.07
    å®Ľ
    -0.07
    duit
    -0.07
    eria
    -0.07
    POSITIVE LOGITS
     somehow
    0.12
     subtle
    0.11
     subtly
    0.10
    å¾®å¦Ļ
    0.08
    æŁIJç§į
    0.08
    _COMPILER
    0.08
     somew
    0.07
    åľ¨çĶ³è¯·
    0.07
     somewhere
    0.07
    被认为
    0.07
    Activations Density 0.010%

    No Known Activations