© 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. 12170
    Prev
    Next
    INDEX
    Explanations

    video submission guidelines

    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
    यà¥ĩ
    -0.08
    -scrollbar
    -0.08
    orso
    -0.08
    apus
    -0.08
    ä½Ĩçİ°åľ¨
    -0.07
    ORS
    -0.07
    itura
    -0.07
    orsi
    -0.07
    roach
    -0.07
    apul
    -0.07
    POSITIVE LOGITS
    arrer
    0.07
    ãģĭãĤĬ
    0.07
    OLO
    0.06
    eza
    0.06
    born
    0.06
    丹
    0.06
    à¸Ľà¸£à¸°à¸ģาร
    0.06
    èĪĪ
    0.06
    ikin
    0.06
    ãĢİ
    0.06
    Activations Density 0.001%

    No Known Activations