© 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. 47365
    Prev
    Next
    INDEX
    Explanations

    indefinite negative terms

    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
    inato
    -0.08
    éĹŃå¡ŀ
    -0.07
     congest
    -0.07
    éļıé£İ
    -0.07
    碾
    -0.07
    ç»Ĩ
    -0.07
     BIN
    -0.07
     Blitz
    -0.06
    /token
    -0.06
    ocard
    -0.06
    POSITIVE LOGITS
     negativity
    0.11
     Negative
    0.11
     negative
    0.11
    è´Ł
    0.10
    -negative
    0.10
    Negative
    0.10
    negative
    0.10
    è²ł
    0.09
    _negative
    0.09
    egative
    0.09
    Activations Density 0.005%

    No Known Activations