© 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. 28211
    Prev
    Next
    INDEX
    Explanations

    noted that

    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
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.08
    ä¾ĭå¦Ĥ
    -0.07
    à¸¹à¸Ľ
    -0.07
     something
    -0.06
     vou
    -0.06
    æį®è¯´
    -0.06
    å¦Ĥä¸ĭ
    -0.06
     Cos
    -0.06
    æľīä¸Ģ次
    -0.06
     напÑĢимеÑĢ
    -0.06
    POSITIVE LOGITS
    /respond
    0.08
    åıªè¦ģæĪij们
    0.08
    ulon
    0.07
    åºĶæīĭ
    0.07
    monto
    0.07
    .removeChild
    0.07
    æĥ³æĸ¹
    0.07
     respondi
    0.07
     fél
    0.07
    OrFail
    0.07
    Activations Density 0.317%

    No Known Activations