© 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. 43067
    Prev
    Next
    INDEX
    Explanations

    DECISION

    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
     i
    -0.06
    ç¨
    -0.06
     first
    -0.06
     –,
    -0.06
    éĵģçļ®
    -0.06
     afterwards
    -0.06
    Ñīина
    -0.06
     nay
    -0.06
    åIJİåį³
    -0.06
     after
    -0.06
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.08
    tuu
    0.08
    çļĦæīĢæľīä½ľåĵģ
    0.08
     Bör
    0.08
    .removeAll
    0.08
    åİ»ä½ķ
    0.08
    orius
    0.08
    _processors
    0.08
     súper
    0.08
    ÐĵлавнÑĭе
    0.08
    Activations Density 0.497%

    No Known Activations