© 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. 37873
    Prev
    Next
    INDEX
    Explanations

    i followed by a verb

    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
    asters
    -0.08
    ÑģÑĤÑĬ
    -0.07
    ¶
    -0.07
    umer
    -0.07
    èĩªé¦ĸ
    -0.07
    годи
    -0.07
    ighthouse
    -0.07
     activeClassName
    -0.07
    ERVED
    -0.07
    ARIANT
    -0.06
    POSITIVE LOGITS
     Sanchez
    0.07
    pty
    0.07
    rech
    0.07
    setValue
    0.07
     sanitari
    0.07
    æŶåĢĻ
    0.07
    lete
    0.07
     Từng
    0.06
    OPP
    0.06
    penas
    0.06
    Activations Density 0.002%

    No Known Activations