© 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. 50950
    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
    åĬ¿å¿ħ
    -0.07
    elaar
    -0.07
    owitz
    -0.07
    λοι
    -0.07
    å¢ħ
    -0.07
    .onreadystatechange
    -0.07
    ç½ijåıĭè¯Ħ论
    -0.07
    _CONFIGURATION
    -0.07
    åĩºä¾ĨçļĦ
    -0.07
    llx
    -0.07
    POSITIVE LOGITS
    aping
    0.07
    移éĢģ
    0.07
     Flake
    0.07
    esture
    0.06
    äºĨçĤ¹
    0.06
    大åħ¬
    0.06
    feuille
    0.06
    uchy
    0.06
    .cloudflare
    0.06
    <|im_end|>
    0.06
    Activations Density 0.000%

    No Known Activations