© 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. 48234
    Prev
    Next
    INDEX
    Explanations

    Q factor and resonators

    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
    eldon
    -0.07
     اÙĦرÙħ
    -0.07
    bam
    -0.07
     Congo
    -0.07
    ince
    -0.06
    ossa
    -0.06
    åĪĨå¸ĥ
    -0.06
     Dock
    -0.06
    æı
    -0.06
     cab
    -0.06
    POSITIVE LOGITS
     tuned
    0.08
    ä¸īé«ĺ
    0.08
     reson
    0.08
    aiss
    0.07
    æ¶īéĩijèŀį
    0.07
     Futter
    0.07
    è®©ä½łä»¬
    0.07
     tune
    0.07
    è¶Ĭé«ĺ
    0.07
     tunes
    0.07
    Activations Density 0.010%

    No Known Activations