© 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. 42659
    Prev
    Next
    INDEX
    Explanations

    suspect/suspected

    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
    almente
    -0.09
    _stderr
    -0.08
    engi
    -0.08
    aining
    -0.08
    ality
    -0.07
    äch
    -0.07
    arily
    -0.07
    ialized
    -0.07
    ôm
    -0.07
    ained
    -0.07
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.10
     suspect
    0.09
    worthy
    0.09
    æĢĢçĸij
    0.09
    ä¸įåĨ³
    0.08
    çļĦ缮åħī
    0.08
    çĸij
    0.08
    éĩįéĩįçļĦ
    0.08
    pecting
    0.08
    uous
    0.08
    Activations Density 0.058%

    No Known Activations