© 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. 30321
    Prev
    Next
    INDEX
    Explanations

    order and parameters

    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
    mith
    -0.11
    оÑıÑĤ
    -0.08
    anches
    -0.07
    aghetti
    -0.07
    opal
    -0.07
    ÙĪرÙĩا
    -0.07
     okaz
    -0.07
    yton
    -0.06
    ames
    -0.06
    AMES
    -0.06
    POSITIVE LOGITS
    å±Ĥ
    0.08
    uder
    0.08
    ener
    0.08
    .Layer
    0.08
    èĹıåľ¨
    0.07
    -layer
    0.07
    +m
    0.07
    ulp
    0.07
    upper
    0.07
    å©
    0.07
    Activations Density 0.009%

    No Known Activations