© 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. 29724
    Prev
    Next
    INDEX
    Explanations

    as a barrier to or enhances

    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
     hend
    -0.07
    ÑģÑĤÑĬ
    -0.07
    mil
    -0.07
    din
    -0.07
    ingin
    -0.06
    à¹īา
    -0.06
     somew
    -0.06
    Av
    -0.06
    sin
    -0.06
     DISCLAIMER
    -0.06
    POSITIVE LOGITS
    жиÑĤе
    0.08
    =config
    0.08
    OLID
    0.08
    ç»ĥåħµ
    0.08
    opsis
    0.07
    åĽ½æ³°
    0.07
    ames
    0.07
    andet
    0.07
    ä¹ĭçľ¼
    0.07
    ForObject
    0.07
    Activations Density 0.168%

    No Known Activations