© 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. 15311
    Prev
    Next
    INDEX
    Explanations

    less, low, smaller, missing

    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
     excess
    -0.08
    åĬ¨è¾Ħ
    -0.08
     berlebihan
    -0.07
    ahead
    -0.07
    è¿ĩéĩı
    -0.07
    ä¹±
    -0.07
    egn
    -0.07
    ä¸ĢæŶ
    -0.07
    è¶ħåĩºäºĨ
    -0.07
    è¶ħè¶ĬäºĨ
    -0.07
    POSITIVE LOGITS
     missing
    0.14
    missing
    0.13
     insufficient
    0.12
    æĺ¯ä¸įå¤Ł
    0.12
     Missing
    0.12
    Missing
    0.11
    太å°ij
    0.11
    éĶĻ失
    0.11
     lacking
    0.11
    ä¸įå¤Ł
    0.11
    Activations Density 0.325%

    No Known Activations