© 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. 39328
    Prev
    Next
    INDEX
    Explanations

    foo after 0

    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
    æ±ŁåĮĹ
    -0.08
    wana
    -0.08
    opan
    -0.08
    ukah
    -0.08
    ents
    -0.08
    åĥıæĪij
    -0.07
    ser
    -0.07
    jumlah
    -0.07
    oho
    -0.07
    unge
    -0.07
    POSITIVE LOGITS
    åĪĿ次
    0.06
    cz
    0.06
    اء
    0.06
    wez
    0.06
    çī¹åĭĴ
    0.06
    unde
    0.06
     done
    0.06
    è°ĥæŁ¥çłĶ究
    0.06
     amd
    0.06
    obel
    0.06
    Activations Density 0.004%

    No Known Activations