© 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. 21643
    Prev
    Next
    INDEX
    Explanations

    professions and roles

    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
    IONE
    -0.07
    anes
    -0.07
    gio
    -0.07
    urit
    -0.07
    ceipt
    -0.07
    olid
    -0.07
     Depos
    -0.07
    ÄĻc
    -0.07
    tiv
    -0.07
    -errors
    -0.07
    POSITIVE LOGITS
    ssen
    0.07
    -like
    0.07
    å¿ħå¤ĩçļĦ
    0.07
    åIJĮ人
    0.06
    èĩªå·±çļĦæĥħ绪
    0.06
    fish
    0.06
    HEMA
    0.06
    ä¹Łä¸įæĥ³
    0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.06
    ashian
    0.06
    Activations Density 0.036%

    No Known Activations