© 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. 14240
    Prev
    Next
    INDEX
    Explanations

    findings to establish

    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
    acker
    -0.08
    _plural
    -0.08
     láng
    -0.08
    unter
    -0.07
    named
    -0.07
     zar
    -0.07
    å¿ħä¸įåı¯å°ij
    -0.07
    ä¿ĬæĿ°
    -0.07
    ENC
    -0.07
     lét
    -0.07
    POSITIVE LOGITS
     clues
    0.08
     evidence
    0.08
     alapján
    0.08
    线索
    0.08
    hall
    0.07
    ä¸į足以
    0.07
     enough
    0.07
     suggestive
    0.07
    ä½ľåģĩ
    0.07
    æݨæĸŃ
    0.07
    Activations Density 0.141%

    No Known Activations