© 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. 19586
    Prev
    Next
    INDEX
    Explanations

    minus sign

    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
    ãi
    -0.10
    alik
    -0.09
    alcon
    -0.09
    ienst
    -0.08
    微信æī«ä¸Ģæī«
    -0.07
    iach
    -0.07
    æľĢç»ĪåıĹçĽĬ
    -0.07
    ktop
    -0.07
    enor
    -0.07
     betaal
    -0.07
    POSITIVE LOGITS
     bỼt
    0.08
    idian
    0.07
    eki
    0.07
    oin
    0.07
     unnecessary
    0.07
     лиÑĪ
    0.07
    iseau
    0.07
    æĪĸå°ij
    0.06
     rect
    0.06
    å¤ļä½ĻçļĦ
    0.06
    Activations Density 0.008%

    No Known Activations