© 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. 29600
    Prev
    Next
    INDEX
    Explanations

    singer or vocalist

    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
    ĺ
    -0.09
    gfx
    -0.07
    gestellt
    -0.07
    ÙĨب
    -0.07
    æ©¡èĥ¶
    -0.07
    ANCE
    -0.07
    à¸Ĺาà¸ĩ
    -0.07
    ness
    -0.07
    ños
    -0.06
    éĹªçĿĢ
    -0.06
    POSITIVE LOGITS
    è°£
    0.11
    ularity
    0.10
    æ¼ĶåĶ±
    0.10
    -song
    0.08
     sung
    0.08
    anel
    0.08
    bird
    0.08
     Jewel
    0.08
     sopr
    0.08
    謡
    0.08
    Activations Density 0.078%

    No Known Activations