© 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. 63348
    Prev
    Next
    INDEX
    Explanations

    exceptions and conditions

    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
    ç»°
    -0.08
    egu
    -0.08
    ä¸ĢçĤ¹åĦ¿
    -0.07
    ulich
    -0.07
    çĪĨ
    -0.07
    hint
    -0.07
    åħ¶ä¹IJ
    -0.07
    äºİäºĭ
    -0.06
    ì¦Į
    -0.06
    ä¸Ŀ毫
    -0.06
    POSITIVE LOGITS
    éĻ¤éĿŀ
    0.19
     unless
    0.19
    unless
    0.18
     Unless
    0.17
     except
    0.16
     normally
    0.15
    Unless
    0.15
     sauf
    0.15
    except
    0.15
     Except
    0.15
    Activations Density 0.239%

    No Known Activations