© 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. 15108
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <|box_end|>
    -0.09
    åľ°ä¹ħ
    -0.09
    enan
    -0.08
    æľªå®Įå¾ħç»Ń
    -0.08
    ä¸ĭ载次æķ°
    -0.08
    å·§
    -0.07
    аÑĢе
    -0.07
     THEME
    -0.07
    TEE
    -0.07
    ARENT
    -0.07
    POSITIVE LOGITS
    нев
    0.07
    icle
    0.06
     ruim
    0.06
     ÑģÑĤÑĢÑĥ
    0.06
    ä¸ĢæŀĿ
    0.06
     tact
    0.06
    yst
    0.06
    enc
    0.06
    é«ĺ产
    0.06
    op
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.