© 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. 31521
    Prev
    Next
    INDEX
    Explanations

    analogies and comparisons

    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
     ext
    -0.07
    _IDENTIFIER
    -0.06
    vert
    -0.06
    ç·
    -0.06
     asc
    -0.06
    迹
    -0.06
    _PREF
    -0.06
    _CUBE
    -0.06
     Melo
    -0.06
    	ext
    -0.06
    POSITIVE LOGITS
     analogy
    0.22
     metaphor
    0.19
    æ¯Ķåĸ»
    0.19
    ç±»æ¯Ķ
    0.18
    -like
    0.16
     analog
    0.15
     analogous
    0.15
     liken
    0.14
     analogue
    0.14
     layaknya
    0.14
    Activations Density 0.312%

    No Known Activations