© 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. 17309
    Prev
    Next
    INDEX
    Explanations

    filtering and numbering

    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
    ±
    -0.07
     ad
    -0.06
    thur
    -0.06
    onna
    -0.06
    çĥģ
    -0.06
    onha
    -0.06
    æĢ§ä»¥åıĬ
    -0.06
    çĶ¨ä½ľäººåIJį
    -0.06
    çŃīæīĭ段
    -0.06
    åı¸ç©º
    -0.06
    POSITIVE LOGITS
    plorer
    0.08
    鼷
    0.07
    plode
    0.07
    udios
    0.07
    лÑİÑĤ
    0.07
    lug
    0.07
    å°±åľ¨è¿Ļ
    0.07
    å°±è¿Ļä¹Ī
    0.07
    лиÑĢÑĥ
    0.07
    ä»İè¿ĻéĩĮ
    0.07
    Activations Density 0.010%

    No Known Activations