© 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. 58087
    Prev
    Next
    INDEX
    Explanations

    election, about, suit, river, war

    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
    haps
    -0.10
    éľĦ
    -0.08
    bote
    -0.07
    rah
    -0.07
    otá
    -0.07
    /../
    -0.07
    startsWith
    -0.07
     Mede
    -0.07
    afx
    -0.07
    Ùĥات
    -0.07
    POSITIVE LOGITS
    istr
    0.06
    ä¸ĩä¸ĩ
    0.06
    èĶ«
    0.06
    ä¸İæѤ
    0.06
    æįŁ
    0.06
    nac
    0.06
    å¥ĩèij©
    0.06
    ustom
    0.06
    ä¿ĿæĮģ稳å®ļ
    0.06
    åIJĥèĤī
    0.06
    Activations Density 0.754%

    No Known Activations