© 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. 42337
    Prev
    Next
    INDEX
    Explanations

    condition, marketing, resource, diversity, community

    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
    OptionsMenu
    -0.08
    çİĭéĩij
    -0.08
    åĩłä¸ĩ
    -0.07
    åıijå±ķåĴĮæĶ¹éĿ©
    -0.07
    åĩłä¹İéĥ½æĺ¯
    -0.07
    agu
    -0.07
    æŃ¥å±¥
    -0.07
    Mocks
    -0.07
    arges
    -0.07
    æīĵæī«åį«çĶŁ
    -0.07
    POSITIVE LOGITS
     &
    0.10
    vs
    0.08
    &
    0.08
    /or
    0.08
     vs
    0.07
    ï¼ı
    0.07
    /Public
    0.07
    &a
    0.07
    -/
    0.07
    /
    0.07
    Activations Density 0.200%

    No Known Activations