© 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. 46286
    Prev
    Next
    INDEX
    Explanations

    maintains the

    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
     comp
    -0.06
     distingue
    -0.06
     oblig
    -0.06
    è¿ħ
    -0.06
     Hyde
    -0.06
    _pad
    -0.06
    åĴĮæĶ¹åĸĦ
    -0.06
    çĩİ
    -0.06
    æ¶īæ°´
    -0.06
    lace
    -0.06
    POSITIVE LOGITS
    å°¾éĥ¨
    0.08
    ufer
    0.08
    ssen
    0.08
    为åIJĮåѦ们
    0.08
    หาà¸ĩ
    0.08
    æĹ¥åĪ¶
    0.08
    ogat
    0.08
    imente
    0.08
    isses
    0.07
    æłĪ
    0.07
    Activations Density 0.001%

    No Known Activations