© 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. 22514
    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
    ä¸įèĥľæĶ¶
    -0.07
    eroy
    -0.07
    amet
    -0.07
     Äijặn
    -0.07
    å®ŀéĻħéľĢæ±Ĥ
    -0.07
    æļ§
    -0.07
    ERING
    -0.07
    á»ģm
    -0.07
    çĤ¹æ»´
    -0.07
    úst
    -0.07
    POSITIVE LOGITS
    ä¸Ĭå½ĵ
    0.08
    otch
    0.07
    Ø·ÙĨ
    0.07
    nsk
    0.06
    PLICATION
    0.06
    ifik
    0.06
     WAR
    0.06
    lai
    0.06
    ataires
    0.06
    sky
    0.06
    Activations Density 0.000%

    No Known Activations