© 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. 25286
    Prev
    Next
    INDEX
    Explanations

    medical and scientific suffixes

    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
    geg
    -0.06
    åħ³åĪĩ
    -0.06
    блÑĥ
    -0.06
    åĽĽå°Ħ
    -0.06
    åı¯èĩªè¡Į
    -0.06
    ysi
    -0.06
     Regents
    -0.06
    endregion
    -0.06
    åĩĮåİī
    -0.06
    åĪĩ
    -0.06
    POSITIVE LOGITS
    åīįç¨ĭ
    0.08
    åį³çĶ¨
    0.07
    éĽģ
    0.07
    ä¸Ģåĵģ
    0.07
    åīįéĢĶ
    0.07
    zung
    0.07
    hani
    0.07
    à¤Ĥà¤Ĺ
    0.07
    xa
    0.07
     Bons
    0.07
    Activations Density 0.322%

    No Known Activations