© 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. 56194
    Prev
    Next
    INDEX
    Explanations

    collecting data

    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
     Civile
    -0.08
    uschen
    -0.07
    laÅŁ
    -0.07
    èģĮå®Ī
    -0.06
     Ñģобой
    -0.06
    èħ¾èħ¾
    -0.06
    uous
    -0.06
    ient
    -0.06
    hafte
    -0.06
    entially
    -0.06
    POSITIVE LOGITS
    åĪ°çļĦ
    0.10
     ÑĥÑĢожаÑı
    0.10
    รวà¸ļรวม
    0.10
    OrUpdate
    0.09
    ifornia
    0.09
    åĴĮåĪ©çĶ¨
    0.08
    ings
    0.08
    ables
    0.08
    anea
    0.08
    /display
    0.08
    Activations Density 0.066%

    No Known Activations