© 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. 16347
    Prev
    Next
    INDEX
    Explanations

    needs improvement or attention

    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
    atis
    -0.07
    _PRED
    -0.07
    aram
    -0.07
    avit
    -0.07
    å¤ŁçĶ¨
    -0.06
    ützen
    -0.06
    并使çĶ¨
    -0.06
    λÏİν
    -0.06
    utsche
    -0.06
    yron
    -0.06
    POSITIVE LOGITS
     urgently
    0.11
     urgente
    0.10
     dringend
    0.09
     absolument
    0.09
     urgent
    0.09
    ä¸ĢæıIJ
    0.09
    needs
    0.09
     ASAP
    0.08
     вним
    0.08
     ÑģÑĢоÑĩно
    0.08
    Activations Density 0.196%

    No Known Activations