© 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. 29241
    Prev
    Next
    INDEX
    Explanations

    increasingly critical services

    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
    eszt
    -0.07
    ellas
    -0.07
    à®±à¯Ī
    -0.07
    .serializer
    -0.07
     misog
    -0.07
    fér
    -0.07
     Komp
    -0.07
    è¿°
    -0.07
     jeito
    -0.07
    kse
    -0.07
    POSITIVE LOGITS
    irian
    0.07
    ikan
    0.07
    /ss
    0.07
    åk
    0.07
    izable
    0.07
    ateg
    0.06
     cushions
    0.06
    /cs
    0.06
    Ĭ
    0.06
    .Criteria
    0.06
    Activations Density 0.039%

    No Known Activations