© 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. 31571
    Prev
    Next
    INDEX
    Explanations

    damage, cracks, fracture, localized

    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
    åıĺåĬ¨
    -0.08
    çĴŁ
    -0.08
    dil
    -0.07
     ferment
    -0.07
     reim
    -0.07
    éĩįåıł
    -0.07
    转æį¢åĻ¨
    -0.07
    æĭ¨
    -0.07
     decad
    -0.07
     Ents
    -0.06
    POSITIVE LOGITS
    amage
    0.10
     rupture
    0.09
     localized
    0.09
     оÑĩа
    0.08
    èĸĦå¼±çݯèĬĤ
    0.08
    awali
    0.08
     damage
    0.08
    Localized
    0.08
    çªģçł´åı£
    0.08
     brittle
    0.08
    Activations Density 0.009%

    No Known Activations