© 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. 19806
    Prev
    Next
    INDEX
    Explanations

    headstart / hindsight

    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
    avanaugh
    -0.09
     harsh
    -0.09
     harm
    -0.08
     hardships
    -0.08
    ØŃت
    -0.07
    Hook
    -0.07
    æ°´çĶµç«Ļ
    -0.07
    个çľģ
    -0.07
    ÑħваÑĤ
    -0.07
    ially
    -0.07
    POSITIVE LOGITS
    ancock
    0.18
    ometown
    0.16
    IGHLIGHT
    0.15
    IDDEN
    0.14
    essian
    0.14
    ORIZONTAL
    0.14
    elloworld
    0.14
    indsight
    0.13
    IGHL
    0.13
    amburger
    0.13
    Activations Density 2.068%

    No Known Activations