© 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. 27375
    Prev
    Next
    INDEX
    Explanations

    answer/abstract/tutorial/article/wikia

    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
    ắt
    -0.07
    `.`
    -0.07
    æķĪ
    -0.07
    说罢
    -0.07
    hire
    -0.06
     otor
    -0.06
    imals
    -0.06
    theless
    -0.06
    abat
    -0.06
    åħ·
    -0.06
    POSITIVE LOGITS
    ä¸Ģå¼Ģå§ĭ
    0.08
    ATOM
    0.08
    ÙĪÙī
    0.07
    éĥ½å¼Ģå§ĭ
    0.07
    个éĹ®é¢ĺ
    0.07
    ewood
    0.07
    æĺ¯åĪĨ
    0.07
    avic
    0.07
    wand
    0.07
    _goto
    0.07
    Activations Density 0.006%

    No Known Activations