© 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. 40436
    Prev
    Next
    INDEX
    Explanations

    so, hence, may

    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
    orz
    -0.09
    csol
    -0.08
    ãĥ
    -0.06
    ä¸įåı¯æĪĸ缺
    -0.06
    vist
    -0.06
    win
    -0.06
    éģĹ
    -0.06
    è§Ĩ
    -0.06
    ason
    -0.06
    alas
    -0.06
    POSITIVE LOGITS
    án
    0.08
    å°¤åħ¶
    0.08
    ági
    0.08
    åı¯èĥ½åıijçĶŁ
    0.08
    çī¹åĪ«éĢĤåIJĪ
    0.07
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    0.07
    åħ·ä½ĵéĹ®é¢ĺ
    0.07
    lese
    0.07
    åı¯èĥ½æľī
    0.07
     somewhat
    0.07
    Activations Density 0.041%

    No Known Activations