© 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. 62405
    Prev
    Next
    INDEX
    Explanations

    typographical errors and typos

    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
    IVEN
    -0.09
    åķ§åķ§
    -0.08
    dle
    -0.08
    ready
    -0.08
    èĢ»
    -0.08
    iven
    -0.08
    æ§ĥ
    -0.07
    onet
    -0.07
    è¾¾åħĭ
    -0.07
    nest
    -0.07
    POSITIVE LOGITS
     missing
    0.07
    åķĨåĬ¡ä¸Ńå¿ĥ
    0.06
    .ms
    0.06
     omission
    0.06
    Missing
    0.06
    ëĤĺë§Ī
    0.06
    zilla
    0.06
    ç¹ģå¤ļ
    0.06
    ureau
    0.06
    adow
    0.06
    Activations Density 0.009%

    No Known Activations