© 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. 10940
    Prev
    Next
    INDEX
    Explanations

    code delimiters and objects

    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
    æĢ§æĪĸ
    -0.07
    heid
    -0.07
    zik
    -0.07
    زÙĬ
    -0.07
    å¦ĤçĥŁ
    -0.07
    vel
    -0.07
    ingle
    -0.07
    Ь
    -0.07
    çĥŁ
    -0.06
    /ion
    -0.06
    POSITIVE LOGITS
    thers
    0.07
    GetInstance
    0.06
    theses
    0.06
    èijµèĬ±
    0.06
    lok
    0.06
    çŃ
    0.06
    çŃĶ
    0.06
    steuer
    0.06
    èĴ²
    0.06
    <|box_end|>
    0.06
    Activations Density 0.003%

    No Known Activations