© 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. 4219
    Prev
    Next
    INDEX
    Explanations

    Copyright text and names

    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
    ×ķ×ķ
    -0.08
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    æĩ¿
    -0.07
    linger
    -0.07
    ulich
    -0.06
    FormGroup
    -0.06
    忱
    -0.06
    veli
    -0.06
    ungeon
    -0.06
    ä¸Ń飩
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹ĪéĹ®é¢ĺ
    0.08
    èĩªèº«
    0.08
    ãģķãĤĤ
    0.08
    ÙĦاÙĭ
    0.08
    åıijå±ķæĪIJ为
    0.07
    ä¸įéĢĤ
    0.07
    é«ĺéĢŁè¡Į驶
    0.07
    诸å¦Ĥ
    0.07
    å°ĨæĿ¥
    0.07
    éļ·
    0.07
    Activations Density 0.020%

    No Known Activations