© 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. 30805
    Prev
    Next
    INDEX
    Explanations

    image file extensions

    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
    mil
    -0.07
    d
    -0.07
    .
    -0.07
    -0.06
    s
    -0.06
    occ
    -0.06
     Col
    -0.06
    man
    -0.06
    emi
    -0.06
     sm
    -0.06
    POSITIVE LOGITS
    滥
    0.09
    jukan
    0.08
    ”âĢ¦
    0.08
    åħ¬åı¸çŃī
    0.08
    idential
    0.08
    еÑĤÑĮ
    0.08
    å°¼äºŀ
    0.08
    äºİå¿ĥ
    0.08
     obsta
    0.08
    æű
    0.08
    Activations Density 0.201%

    No Known Activations