© 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. 26844
    Prev
    Next
    INDEX
    Explanations

    accepted

    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
     appunto
    -0.06
    æĢ»ç»ĵå¦Ĥä¸ĭ
    -0.06
    åĨµ
    -0.06
    ä¸ĭåIJĮ
    -0.06
    ä»ħæѤ
    -0.06
    <|quad_end|>
    -0.05
    ãģªãģ®ãģ§ãģĹãĤĩãģĨãģĭ
    -0.05
    åħ¨ä½ĵå¹²éĥ¨èģĮå·¥
    -0.05
    çĤ
    -0.05
    POSITIVE LOGITS
     ï¼ļ
    0.09
    !:
    0.09
    ':
    0.09
     meanwhile
    0.08
    )':
    0.08
    伯ä¹IJ
    0.08
    ”:
    0.08
     ():
    0.08
    isy
    0.08
    ":
    0.07
    Activations Density 0.151%

    No Known Activations