© 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. 15977
    Prev
    Next
    INDEX
    Explanations

    blockade, inhibition, antagonists

    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
    bsd
    -0.08
    uga
    -0.07
    ernet
    -0.07
    leness
    -0.07
    ibbon
    -0.06
    emer
    -0.06
    ame
    -0.06
    anium
    -0.06
    inness
    -0.06
    大åħ¬
    -0.06
    POSITIVE LOGITS
    /block
    0.09
    æĪĸçĶ¨
    0.09
    éĺ»æĸŃ
    0.08
    æĪĸåĪłéĻ¤
    0.08
    åıĸä¸ĭ
    0.07
    zia
    0.07
    é¢ĦåħĪ
    0.07
    hout
    0.07
    å°±åıĺå¾Ĺ
    0.07
    .bundle
    0.07
    Activations Density 0.439%

    No Known Activations