© 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. 61446
    Prev
    Next
    INDEX
    Explanations

    chondrogenesis, compomer, arsort.js, Residence Inn, growth company, Bloom's syndrome, Purging Disorder

    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
    è½½
    -0.07
    æŀĿ
    -0.07
    /cop
    -0.06
    <html
    -0.06
    å°¤åħ¶æĺ¯
    -0.06
    çī¹æĭī
    -0.06
    ä¸įè¡°
    -0.06
    éģį
    -0.06
    olla
    -0.06
    -it
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.08
    another
    0.08
    rase
    0.07
    asal
    0.07
    appen
    0.07
    ciso
    0.07
    ìĸ´ëĵľ
    0.07
    IZER
    0.07
    ëĵł
    0.07
    éĿ¢ä¸´çļĦéĹ®é¢ĺ
    0.07
    Activations Density 0.260%

    No Known Activations