© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40726
    Prev
    Next
    INDEX
    Explanations

    wrong answers or suggestions

    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
    éĽ
    -0.06
    ppe
    -0.06
    å¾Īæĺİæĺ¾
    -0.06
    éĥİ
    -0.06
    lds
    -0.06
    æĺ¯ä¸ĢåĪĩ
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    åį´å§ĭç»Ī
    -0.06
    åıijè§ī
    -0.06
    -0.06
    POSITIVE LOGITS
    opil
    0.08
     somehow
    0.08
    ebre
    0.08
    éĶĻ误æĪĸ
    0.08
    æ¸ħ空
    0.08
    好æĥ³
    0.07
    ëħIJ
    0.07
    å»¶æľŁ
    0.07
    umah
    0.07
    enov
    0.07
    Activations Density 0.002%

    No Known Activations