© 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. 46874
    Prev
    Next
    INDEX
    Explanations

    mathematical proof or hypothesis

    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
    å½ĵæŶ
    -0.07
    æ´Ľå¤«
    -0.07
    ...
    -0.07
    ewn
    -0.06
    DIG
    -0.06
    .Framework
    -0.06
    类似
    -0.06
     Tort
    -0.06
    ****
    -0.06
    ange
    -0.06
    POSITIVE LOGITS
     indeed
    0.08
    ouncill
    0.08
    è§Ħ模为
    0.08
    微信æī«ä¸Ģæī«
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    çŃīåIJĦ项
    0.07
    éĶ¢
    0.07
     Strut
    0.07
    (),"
    0.07
    ornado
    0.07
    Activations Density 0.003%

    No Known Activations