© 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. 1300
    Prev
    Next
    INDEX
    Explanations

    the rest

    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
    sure
    -0.08
    Sure
    -0.07
     Sure
    -0.07
    æĹłçĸij
    -0.07
    åĪĨ许
    -0.07
    ello
    -0.07
    evity
    -0.07
     Chapman
    -0.06
     sure
    -0.06
    ison
    -0.06
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.12
    åħ¶é¤ĺ
    0.09
     rest
    0.08
     оÑģÑĤалÑĮнÑĭе
    0.08
    å°ijéĩı
    0.08
     meanwhile
    0.07
     باÙĤÙĬ
    0.07
    .rdf
    0.07
    .rest
    0.07
    ih
    0.07
    Activations Density 0.072%

    No Known Activations