© 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. 17179
    Prev
    Next
    INDEX
    Explanations

    part of a component

    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
    ...
    -0.07
    irik
    -0.06
    erson
    -0.06
    iders
    -0.06
    çīĽè§Ĵ
    -0.06
    马è¹Ħ
    -0.06
    irie
    -0.06
    âĢ¦
    -0.06
    åħ¶ä»ĸ
    -0.06
    berman
    -0.06
    POSITIVE LOGITS
    .weight
    0.08
    ième
    0.08
    大é¤IJ
    0.07
    æĹ¥æĹ©ä¸Ĭ
    0.07
    izr
    0.07
    ighb
    0.07
    cule
    0.07
    cÄĥ
    0.07
    ä¿¡æģ¯ç½ij
    0.07
    rena
    0.07
    Activations Density 0.088%

    No Known Activations