© 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. 56961
    Prev
    Next
    INDEX
    Explanations

    ensemble partitioning, information matrix

    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
     softer
    -0.07
    GRADE
    -0.07
    elin
    -0.07
    触åıij
    -0.06
    çĬĢåĪ©
    -0.06
    é¢ł
    -0.06
    reb
    -0.06
    çºł
    -0.06
    ouri
    -0.06
    ce
    -0.06
    POSITIVE LOGITS
    yty
    0.08
     Cair
    0.08
    orno
    0.08
     ensemble
    0.07
    ä¸įåĢ¦
    0.07
    åĢ¼å®Ī
    0.07
    Ĩµ
    0.07
    ç¦ıæ°Ķ
    0.07
    ä¸Ģ课
    0.07
    说æľī
    0.07
    Activations Density 0.001%

    No Known Activations