© 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. 60971
    Prev
    Next
    INDEX
    Explanations

    descriptive fields

    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
     dér
    -0.08
    utos
    -0.08
    oges
    -0.08
    кала
    -0.08
    æĪijåĪļ
    -0.08
    ania
    -0.08
    ovre
    -0.08
    ispens
    -0.07
    loys
    -0.07
    elan
    -0.07
    POSITIVE LOGITS
    çIJĨ
    0.06
    çIJĨçļĦ
    0.06
     Stap
    0.06
    åĩĽ
    0.06
    addField
    0.06
    :
    0.05
    ÅĽnie
    0.05
    å¢ĥ
    0.05
    getDisplay
    0.05
     ger
    0.05
    Activations Density 0.022%

    No Known Activations