© 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. 18676
    Prev
    Next
    INDEX
    Explanations

    field into, metal against, audio after

    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
    chenk
    -0.10
    ä¸Ĭ好
    -0.09
    sville
    -0.09
    åIJijèį£
    -0.09
    pickle
    -0.09
    <<<<
    -0.09
    asten
    -0.09
     lekk
    -0.09
    erre
    -0.09
    cret
    -0.09
    POSITIVE LOGITS
    ...
    0.07
     followed
    0.07
     Chall
    0.06
    0.06
    忽çĦ¶
    0.06
    1
    0.06
     accompanied
    0.06
     unexpectedly
    0.06
    ä½łä¼ļ
    0.06
     ...
    0.06
    Activations Density 0.520%

    No Known Activations