© 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. 1045
    Prev
    Next
    INDEX
    Explanations

    was, might, are, enough, it

    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
    å§ĭ
    -0.09
    gor
    -0.06
    æ´²
    -0.06
     b
    -0.06
    iterals
    -0.06
     corresponding
    -0.06
    建å®ī
    -0.06
    éĢ
    -0.06
    çIJħ
    -0.06
    è¿IJåĬ¨åĴĮ
    -0.06
    POSITIVE LOGITS
    è¶³å¤Ł
    0.08
    ĮĢ
    0.08
     realistically
    0.08
    вÑĢо
    0.08
    åĵ¼åĵ¼
    0.08
    Eventually
    0.08
    DELAY
    0.08
    ietta
    0.07
    nul
    0.07
    ringer
    0.07
    Activations Density 0.008%

    No Known Activations