© 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. 18251
    Prev
    Next
    INDEX
    Explanations

    muscles and physical constraints

    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
     Salut
    -0.09
    uber
    -0.07
     едино
    -0.07
    à¹Ĥà¸Ī
    -0.07
     muj
    -0.07
     ub
    -0.07
     ubiqu
    -0.07
    æ·ĺæ±°
    -0.07
    Mapper
    -0.07
     qualified
    -0.07
    POSITIVE LOGITS
     constraints
    0.09
    _constraints
    0.09
     constraint
    0.09
     Constraint
    0.09
    约æĿŁ
    0.08
    èĩªçĶ±çļĦ
    0.08
    Constraints
    0.08
     constrained
    0.08
     CONSTRAINT
    0.08
     Heim
    0.08
    Activations Density 0.018%

    No Known Activations