© 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. 41270
    Prev
    Next
    INDEX
    Explanations

    output statements

    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
    ooth
    -0.08
    illet
    -0.07
    å°±è§ģ
    -0.07
    æĪijä¸įæĥ³
    -0.07
    è¿Ļä¹Īåģļ
    -0.06
    —from
    -0.06
    åĪ©çī©
    -0.06
    ä¸ĢæĹł
    -0.06
    razier
    -0.06
    å¾Ĺåħ¶
    -0.06
    POSITIVE LOGITS
    èѦ
    0.08
    Legend
    0.08
    ostr
    0.08
    è¿Ī
    0.07
    ptune
    0.07
    agini
    0.07
    apol
    0.07
    æŃ£åľ¨
    0.07
    echa
    0.07
    æ²ī
    0.07
    Activations Density 0.116%

    No Known Activations