© 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. 16202
    Prev
    Next
    INDEX
    Explanations

    JavaCPP

    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
    çĶ±æѤ
    -0.08
    çĶ±å¸Ĥ
    -0.08
    æľī人
    -0.07
    Charset
    -0.07
    ahui
    -0.07
    ÑĥÑĢо
    -0.07
    обе
    -0.07
    ijker
    -0.07
     voller
    -0.07
    äºİæѤ
    -0.07
    POSITIVE LOGITS
    带åĪ°
    0.09
    çľĭåĩºæĿ¥
    0.09
    è®°å½ķä¸ĭæĿ¥
    0.09
    以ä¸ĭæĸ¹å¼ı
    0.09
    èģĶ系起æĿ¥
    0.08
     soins
    0.08
    说äºĨç®Ĺ
    0.08
    带åĪ°äºĨ
    0.08
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    æīĢåIJ¸å¼ķ
    0.07
    Activations Density 0.149%

    No Known Activations