© 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. 34289
    Prev
    Next
    INDEX
    Explanations

    bolt, Bolt Action, bolt upright

    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
    ingung
    -0.08
    ами
    -0.08
    erre
    -0.08
    -bars
    -0.08
    å®īåĪ©
    -0.07
    dle
    -0.07
    ergestellt
    -0.07
    à¯įப
    -0.07
    ÄĻcz
    -0.07
    essant
    -0.07
    POSITIVE LOGITS
    ÙĪز
    0.07
    ëį°ìļĶ
    0.07
    æĦıä¹īä¸ĬçļĦ
    0.07
    levator
    0.07
    ssa
    0.07
    vation
    0.06
     vector
    0.06
     ÑĢада
    0.06
    chst
    0.06
    neze
    0.06
    Activations Density 0.003%

    No Known Activations