© 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. 15166
    Prev
    Next
    INDEX
    Explanations

    sequential, intermittent, frequency, conditional

    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
    ival
    -0.07
    海港
    -0.06
    ells
    -0.06
     hÃłi
    -0.06
    ä¸įå¾Ĺ
    -0.06
    ç¹ģæĿĤ
    -0.06
    èĤĩ
    -0.06
    åħħå®ŀèĩªå·±
    -0.06
    ading
    -0.06
    olf
    -0.05
    POSITIVE LOGITS
    stel
    0.07
    ä¸įåĥı
    0.07
    å§ĵ
    0.07
    AGIC
    0.07
    plevel
    0.07
    CTIONS
    0.07
    ä¸ĢæĿ¡è¡Ĺ
    0.07
    .band
    0.07
    aje
    0.07
    mgr
    0.07
    Activations Density 0.047%

    No Known Activations