© 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. 24314
    Prev
    Next
    INDEX
    Explanations

    Chevalier, Cheka, Cheeger, Chechnya

    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
    çĿĽ
    -0.07
    ç¯Ŀ
    -0.07
    duct
    -0.07
    toon
    -0.06
    inkel
    -0.06
    aven
    -0.06
    åľ¨çĽ®
    -0.06
    اØŃ
    -0.06
    èĬĿåĬł
    -0.06
    çĶ°éĩİ
    -0.06
    POSITIVE LOGITS
    aufs
    0.09
    -UA
    0.08
    ragon
    0.08
    itr
    0.08
    urts
    0.07
    urger
    0.07
    endants
    0.07
    rites
    0.07
    ears
    0.07
    idades
    0.07
    Activations Density 0.001%

    No Known Activations