© 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. 3423
    Prev
    Next
    INDEX
    Explanations

    copyright statements

    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
    quete
    -0.08
    lvl
    -0.08
    cene
    -0.08
    å²³
    -0.08
    _GRE
    -0.07
    ìī½
    -0.07
    èĶ¼
    -0.07
    splash
    -0.07
    æĬķ稿éĤ®ç®±
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    POSITIVE LOGITS
    çĵ
    0.07
    ji
    0.07
    å¯¹åľ¨
    0.06
     اÙĦÙħؤ
    0.06
    dj
    0.06
    uder
    0.06
    ÑģÑĤÑĥ
    0.06
    ramid
    0.06
    doc
    0.06
     Rod
    0.06
    Activations Density 0.021%

    No Known Activations