© 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. 17409
    Prev
    Next
    INDEX
    Explanations

    case scenarios and outcomes

    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
    /or
    -0.08
    ackets
    -0.07
     primarily
    -0.06
    ic
    -0.06
    缸åħ³ä¸ļåĬ¡
    -0.06
    wick
    -0.06
     predominantly
    -0.06
    act
    -0.06
    иÑģк
    -0.06
    continu
    -0.06
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.08
    mdat
    0.08
    ligen
    0.08
    æĿ¡ä»¶ä¸ĭ
    0.08
    ī
    0.07
    ehme
    0.07
    vely
    0.07
    yono
    0.07
    emento
    0.07
    çĬ¶æĢģä¸ĭ
    0.07
    Activations Density 0.004%

    No Known Activations