© 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. 58050
    Prev
    Next
    INDEX
    Explanations

    growing and culturing

    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
    å¡ŀ
    -0.08
    森æŀĹéĺ²çģ«
    -0.08
     Survey
    -0.07
     heav
    -0.07
     survey
    -0.07
    åĭĺå¯Ł
    -0.07
    Survey
    -0.07
    é¼
    -0.07
    è½»éĩį
    -0.07
     braking
    -0.07
    POSITIVE LOGITS
    çļĦåŁ¹åħ»
    0.11
     nurturing
    0.11
     вÑĭÑĢаÑīив
    0.11
    åŁ¹åħ»
    0.10
    åŁ¹èĤ²
    0.10
    饲åħ»
    0.10
    ç¹ģæ®ĸ
    0.10
    ç¹ģèĤ²
    0.10
     incub
    0.10
     growth
    0.10
    Activations Density 0.180%

    No Known Activations