© 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. 14676
    Prev
    Next
    INDEX
    Explanations

    plenty of

    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
    -0.14
    zelfde
    -0.11
    纷åijĪ
    -0.10
    jenigen
    -0.10
    åĮªæµħ
    -0.10
    缸è¾ħ缸æĪIJ
    -0.09
    strup
    -0.09
    ลฯ
    -0.09
    ़
    -0.09
    åĭĩå¾Ģ缴åīį
    -0.09
    POSITIVE LOGITS
    æĺİäºĨ
    0.08
    íŀĪ
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    issima
    0.07
    è¿Ļ个éģĵçIJĨ
    0.07
    uous
    0.07
    heits
    0.07
    Ñıд
    0.07
     enough
    0.07
    äºĨ
    0.07
    Activations Density 0.010%

    No Known Activations