© 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. 56319
    Prev
    Next
    INDEX
    Explanations

    Kirby, bin, Lint, Project, gitbook

    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
    zkod
    -0.09
    ovich
    -0.07
    ловиÑĩ
    -0.07
    esda
    -0.07
    _ADC
    -0.07
    bac
    -0.07
    اÙħ
    -0.07
    %p
    -0.07
    幸è¿IJçļĦæĺ¯
    -0.07
     bénéfic
    -0.07
    POSITIVE LOGITS
    éģĩè§ģä½ł
    0.06
     staging
    0.06
    çIJ¼æĸ¯
    0.06
    襲
    0.06
    ://"
    0.06
    isci
    0.06
    ft
    0.06
     Habit
    0.06
    sters
    0.06
     staged
    0.06
    Activations Density 0.318%

    No Known Activations