© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16201
    Prev
    Next
    INDEX
    Explanations

    location notice

    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
    ERN
    -0.08
     doule
    -0.07
    erno
    -0.07
    onger
    -0.07
    gere
    -0.07
    ç¬ijè¯Ŀ
    -0.07
    ç»´å°Ķ
    -0.07
    atik
    -0.07
    ISTS
    -0.07
    tern
    -0.07
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.08
    å½ĵåħ¶
    0.07
    åĩºåħ¶
    0.07
     deren
    0.07
    å¦Ĥæŀľä»ĸ们
    0.07
    åľ¨åħ¶
    0.07
    åĺĽ
    0.07
    æŁIJ人
    0.06
     thereof
    0.06
    éĤ£äºº
    0.06
    Activations Density 0.081%

    No Known Activations