© 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. 30688
    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
    å®ĥæīĢ
    -0.07
    Âł
    -0.07
    认
    -0.06
    ä¸Ģå®ļçļĦ
    -0.06
    	done
    -0.06
    两边çļĦ
    -0.06
    starter
    -0.06
     Maximum
    -0.06
    è®
    -0.06
    ç£Ĭ
    -0.06
    POSITIVE LOGITS
    INGK
    0.09
    第ä¸ĥ
    0.08
    第äºĶ
    0.08
    第åħŃ
    0.08
    ortable
    0.08
     fifth
    0.08
    第åħ«
    0.07
    laut
    0.07
    éĩĮäºļ
    0.07
    wer
    0.07
    Activations Density 0.000%

    No Known Activations