© 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. 1980
    Prev
    Next
    INDEX
    Explanations

    apologies and guilt

    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
    stur
    -0.07
    ëŀľ
    -0.07
    å¸ĮæľĽå¯¹å¤§å®¶æľīæīĢ帮åĬ©
    -0.07
    æ®Ĭ
    -0.06
    å¥Īä½ķ
    -0.06
    adesh
    -0.06
    女éĥİ
    -0.06
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    -0.06
    ÑĤÑĥÑĢа
    -0.06
    åı¯éĿł
    -0.06
    POSITIVE LOGITS
    çĸļ
    0.11
    è¿ĩéĶĻ
    0.11
    èĩªè´£
    0.10
     lá»Ĺi
    0.10
    æĹłæĦ§
    0.10
    æĹłæĤĶ
    0.09
    è¿ĩ失
    0.09
    认éĶĻ
    0.09
     culpa
    0.09
    æĤĶ
    0.09
    Activations Density 0.058%

    No Known Activations