© 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. 38546
    Prev
    Next
    INDEX
    Explanations

    given, granted, or allocated

    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
    occa
    -0.08
     ChÃŃ
    -0.08
    ogg
    -0.07
    кл
    -0.07
    åIJĮåIJį
    -0.07
    vera
    -0.07
     chÃŃ
    -0.07
    èĢĹæŶ
    -0.07
    alsy
    -0.07
     rall
    -0.07
    POSITIVE LOGITS
     granted
    0.17
     allowance
    0.13
     allotted
    0.13
    åħģ许
    0.13
     granting
    0.12
    æİĪäºĪ
    0.12
    Granted
    0.12
     allocated
    0.12
     allowed
    0.12
    ãĤĴä¸İ
    0.12
    Activations Density 0.414%

    No Known Activations