© 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. 22277
    Prev
    Next
    INDEX
    Explanations

    multiple commas, hyphens, nbsp

    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
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    -0.08
    Bay
    -0.07
    漪
    -0.07
    engen
    -0.07
    lessness
    -0.07
    andan
    -0.06
    verband
    -0.06
     "_
    -0.06
    less
    -0.06
    otto
    -0.06
    POSITIVE LOGITS
    .gwt
    0.08
    orts
    0.07
    (Expected
    0.07
    onar
    0.07
    keley
    0.07
    оÑģÑĥ
    0.07
     Russo
    0.07
    à¹Ĩ
    0.06
    âĢ¦"
    0.06
    énées
    0.06
    Activations Density 0.007%

    No Known Activations