© 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. 4013
    Prev
    Next
    INDEX
    Explanations

    con followed by I or ably

    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
    Ñĥй
    -0.07
    »
    -0.06
    èѬå¦Ĥ
    -0.06
     tv
    -0.06
     [:
    -0.06
    å©
    -0.06
    飶
    -0.06
    DL
    -0.06
    æ¨ĭ
    -0.06
    çĤ
    -0.06
    POSITIVE LOGITS
    zol
    0.08
    obb
    0.08
    olley
    0.08
    éĶĻçļĦ
    0.08
    éĶĻ
    0.08
    /tutorial
    0.08
    лдÑĭ
    0.08
    ×¢×ĵ
    0.08
     mistake
    0.07
    enus
    0.07
    Activations Density 0.060%

    No Known Activations