© 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. 4327
    Prev
    Next
    INDEX
    Explanations

    any or arbitrary noun

    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
    ushima
    -0.08
    eland
    -0.08
    çļĦåħ¸åŀĭ
    -0.08
    å±±éķĩ
    -0.08
     Buf
    -0.08
    aln
    -0.07
    imas
    -0.07
    estone
    -0.07
    _FOREACH
    -0.07
    åħ¸åŀĭ
    -0.07
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.10
     except
    0.10
     Except
    0.09
    Except
    0.08
    except
    0.08
    åıªè¦ģæĺ¯
    0.08
    æĹłè®º
    0.07
     sauf
    0.07
    éĻ¤éĿŀ
    0.06
    æĪĸéĥ¨åĪĨ
    0.06
    Activations Density 0.021%

    No Known Activations