© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    progress bar, interest, income, strength, oxygen, entropy

    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
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.08
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    hofer
    -0.06
    ÅĨ
    -0.06
    èĩªçĦ¶èĢĮ
    -0.06
    ForResult
    -0.06
    ä¸ĭåľº
    -0.06
    infeld
    -0.06
    åıĺåĮĸæĥħåĨµ
    -0.06
    çĬ¹
    -0.06
    POSITIVE LOGITS
    åĨħ容åĮħæĭ¬
    0.08
    代çłģå¦Ĥä¸ĭ
    0.08
    ï¼Ŀï¼Ŀ
    0.08
    :['
    0.08
    以æѤ
    0.07
    Scaled
    0.07
     rnd
    0.07
    åīįåħĪ
    0.07
    éĿ¢ç§¯çº¦
    0.07
    åīįæľī
    0.07
    Activations Density 0.009%

    No Known Activations