© 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. 11350
    Prev
    Next
    INDEX
    Explanations

    syringe and dispenser

    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
    heatmap
    -0.08
     tost
    -0.08
    çĩĥçħ¤
    -0.08
    å¼±çĶµ
    -0.08
    羣å®ŀæĢ§è´Łè´£
    -0.07
    teras
    -0.07
    çĻ»ä¸ĬäºĨ
    -0.07
     expansive
    -0.07
    ä¸ĢéĿ¢
    -0.07
    itest
    -0.07
    POSITIVE LOGITS
    管åĨħ
    0.09
     refill
    0.09
     cap
    0.08
     nozzle
    0.08
    åĺ´
    0.08
     подаÑĩи
    0.08
    æŁĦ
    0.08
    å°Ħåĩº
    0.08
    注å°Ħ
    0.08
    ervoir
    0.08
    Activations Density 0.113%

    No Known Activations