© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56819
    Prev
    Next
    INDEX
    Explanations

    Euler path 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
    зоÑĢ
    -0.08
    _matching
    -0.08
    éĤģ
    -0.08
     bén
    -0.08
    plor
    -0.08
    _modes
    -0.07
    odor
    -0.07
    abor
    -0.07
     cár
    -0.07
    caret
    -0.07
    POSITIVE LOGITS
     constraint
    0.11
     constraints
    0.10
     Constraint
    0.09
    约æĿŁ
    0.09
    constraints
    0.08
    constraint
    0.08
    Constraint
    0.07
     Constraints
    0.07
     constrain
    0.07
    Constraints
    0.07
    Activations Density 0.009%

    No Known Activations