© 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. 23601
    Prev
    Next
    INDEX
    Explanations

    fractions or sequences

    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
    ziÄĻ
    -0.07
    째
    -0.07
    alj
    -0.07
    etat
    -0.07
    dob
    -0.07
    械
    -0.07
    带走äºĨ
    -0.06
    æµģåħī
    -0.06
    ä¸īä½ĵ
    -0.06
    ÑĪÑĤа
    -0.06
    POSITIVE LOGITS
    osite
    0.07
    åıijèĩª
    0.07
    ditor
    0.06
    rence
    0.06
    ersed
    0.06
    ä¹ĭäºİ
    0.06
    illac
    0.06
    å´ĩé«ĺ
    0.06
    avour
    0.06
    imia
    0.06
    Activations Density 0.011%

    No Known Activations