© 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. 64463
    Prev
    Next
    INDEX
    Explanations

    negation or existential clauses

    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
    åĵªäºĽ
    -0.11
     ones
    -0.10
    wissenschaften
    -0.09
     beiden
    -0.09
     themselves
    -0.09
     meisten
    -0.09
     коÑĤоÑĢÑĭе
    -0.09
     are
    -0.08
     jotka
    -0.08
     δÏįο
    -0.08
    POSITIVE LOGITS
     stuff
    0.09
     imagery
    0.08
    对äºİè¿ĻäºĽ
    0.08
    uration
    0.08
     granularity
    0.07
     gente
    0.07
    ç¢
    0.07
     functionality
    0.07
     variety
    0.07
    ertype
    0.07
    Activations Density 0.734%

    No Known Activations