© 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. 997
    Prev
    Next
    INDEX
    Explanations

    information day

    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
    ztat
    -0.07
    áĢĦáĢºáĢ¸
    -0.07
    aln
    -0.07
    {}]
    -0.07
    (man
    -0.07
     Alme
    -0.07
    _through
    -0.07
     korona
    -0.07
    ÅĽni
    -0.07
    ä¸įè¦ģ被
    -0.07
    POSITIVE LOGITS
    çĪ±
    0.07
    æµ
    0.07
    amba
    0.06
     Keh
    0.06
    åĺ¹
    0.06
    åįľ
    0.06
    ymb
    0.06
     COND
    0.06
     Silence
    0.06
    æ¸Ĭ
    0.06
    Activations Density 0.078%

    No Known Activations