© 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. 55668
    Prev
    Next
    INDEX
    Explanations

    VLC, VMware, virtual, vakin

    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
    åħļå§Ķ
    -0.09
     vitale
    -0.07
     varietÃł
    -0.07
    /videos
    -0.07
     viá»ģn
    -0.07
     ventures
    -0.07
     vasta
    -0.07
     visuals
    -0.06
     vision
    -0.06
    è´µå·ŀ
    -0.06
    POSITIVE LOGITS
    engeance
    0.17
    IRTUAL
    0.17
    OLUME
    0.16
    oodoo
    0.16
    ERTICAL
    0.15
    ázquez
    0.14
    ancouver
    0.14
     dụ
    0.13
    agrant
    0.13
    irtual
    0.13
    Activations Density 1.424%

    No Known Activations