© 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. 46608
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    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
    çĴ§
    -0.07
    éłĺ
    -0.07
    è£ĺ
    -0.06
    è·Ľ
    -0.06
    è¿·
    -0.06
     extra
    -0.06
    ücke
    -0.06
    è£ģ
    -0.06
     mand
    -0.06
    extra
    -0.06
    POSITIVE LOGITS
    æ¦Ĥçİĩ
    0.12
     probability
    0.12
    çļĦæ¦Ĥçİĩ
    0.11
     Probability
    0.11
    probability
    0.10
     веÑĢоÑıÑĤноÑģÑĤÑĮ
    0.10
    _probability
    0.10
    Probability
    0.10
     probabilities
    0.10
    åĩłçİĩ
    0.09
    Activations Density 0.005%

    No Known Activations