© 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. 42943
    Prev
    Next
    INDEX
    Explanations

    body, transparent, absorbing

    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
    mack
    -0.08
    鸾
    -0.07
    plen
    -0.07
    æĽ
    -0.07
    åĽ½åľŁ
    -0.07
    çŀ³
    -0.07
    å¼Ģ好
    -0.06
     prek
    -0.06
    禦
    -0.06
    pire
    -0.06
    POSITIVE LOGITS
     internal
    0.09
    åĨħéĥ¨
    0.08
    èĢĹ
    0.08
     internally
    0.08
     redistrib
    0.08
    internal
    0.08
    æ¶ĪèĢĹ
    0.07
    æļĤæŶçļĦ
    0.07
     Internal
    0.07
    ÏģαÏĥ
    0.07
    Activations Density 0.011%

    No Known Activations