© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17896
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    lop
    -0.08
     Schwartz
    -0.07
    ingi
    -0.07
    社交
    -0.06
    éĶ¤
    -0.06
    cope
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
    Defaults
    -0.06
    åıĬ以ä¸ĬåѦåİĨ
    -0.06
    _CAPACITY
    -0.06
    POSITIVE LOGITS
    ikel
    0.08
     Supplement
    0.08
    é«ĺå¯Ĩ
    0.08
    orp
    0.07
    éľĸ
    0.07
    ptime
    0.07
    ìĤ¬ì§Ħ
    0.07
     cá»Ń
    0.07
    å®Ĺ亲
    0.07
    ä¸įæĥĬ
    0.07
    Activations Density 0.000%

    No Known Activations