© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21798
    Prev
    Next
    INDEX
    Explanations

    left and right positioning

    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
    åŀ«
    -0.09
    éĵº
    -0.08
    ÙĦÙĤ
    -0.08
    è¶´åľ¨
    -0.08
    广
    -0.08
     flat
    -0.08
    大æ°Ķ
    -0.08
    éĵºè®¾
    -0.08
    éĵºè£ħ
    -0.07
    å¹³
    -0.07
    POSITIVE LOGITS
    æŁ±
    0.12
     vertical
    0.12
    vertical
    0.11
    Vertical
    0.11
    åŀĤ缴
    0.11
     веÑĢÑĤика
    0.11
    column
    0.11
     Vertical
    0.11
     column
    0.10
    縦
    0.10
    Activations Density 0.136%

    No Known Activations