© 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. 23814
    Prev
    Next
    INDEX
    Explanations

    just followed by related words

    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
    zyst
    -0.09
    stry
    -0.08
    åĮªæµħ
    -0.08
     jopa
    -0.08
    TRL
    -0.08
    iseau
    -0.08
     ëĺIJíķľ
    -0.08
    веÑĢÑĪенно
    -0.07
    并èĮĤ
    -0.07
    æīĢæĢĿ
    -0.07
    POSITIVE LOGITS
    ifying
    0.11
    ness
    0.10
    ifies
    0.10
     kidding
    0.10
    ifications
    0.10
    ifiable
    0.10
    ifi
    0.09
    à¹Ĩ
    0.09
    ified
    0.09
     à¹Ĩ
    0.09
    Activations Density 0.072%

    No Known Activations