© 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. 33960
    Prev
    Next
    INDEX
    Explanations

    suggest leave red line

    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
    erta
    -0.08
    aing
    -0.08
    horn
    -0.08
    åĪ«
    -0.07
    amento
    -0.07
    ÑĢаÑĤа
    -0.07
    ERTA
    -0.07
    jm
    -0.07
    \Collections
    -0.07
     bate
    -0.07
    POSITIVE LOGITS
     Gore
    0.07
    è¿ĻäºĽåĽłç´ł
    0.07
    å°Ĩè¿ĻäºĽ
    0.07
    æīĢæľīè¿ĻäºĽ
    0.07
    ibar
    0.07
    è¿Ļåĩłä¸ª
    0.07
    ä¸Ĭåįĥ
    0.07
    nett
    0.07
    éĢļè¿ĩ以ä¸Ĭ
    0.06
    è¿ĻäºĽ
    0.06
    Activations Density 0.002%

    No Known Activations