© 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. 49655
    Prev
    Next
    INDEX
    Explanations

    separation, stripping, column

    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
    尼奥
    -0.07
     pathology
    -0.07
    atrix
    -0.07
    ÑĬв
    -0.07
    atte
    -0.07
    åħħçĶµ
    -0.06
    é¢Ĩåľ°
    -0.06
    obble
    -0.06
    å¹³å®ī
    -0.06
    attery
    -0.06
    POSITIVE LOGITS
     reflux
    0.08
    éĢĨæµģ
    0.08
    æĬĺ
    0.07
    äºĶ粮液
    0.07
    çĻ½éħĴ
    0.07
    好æĸĩ
    0.07
     liquor
    0.07
    å¡Ķ
    0.07
     Tall
    0.07
    交æį¢
    0.07
    Activations Density 0.015%

    No Known Activations