© 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. 32560
    Prev
    Next
    INDEX
    Explanations

    parentheses `()` or curly braces `{}`

    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
    ive
    -0.07
    ley
    -0.07
    imes
    -0.07
    çĻ½éĩij
    -0.07
    oly
    -0.07
    ivot
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    kit
    -0.07
    |-
    -0.07
    ówe
    -0.07
    POSITIVE LOGITS
    orex
    0.08
    innan
    0.07
    ä¸į妨
    0.07
    elden
    0.07
    angk
    0.06
    emps
    0.06
    è¹Ń
    0.06
    强迫
    0.06
    etre
    0.06
    áĥ§
    0.06
    Activations Density 0.002%

    No Known Activations