© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2346
    Prev
    Next
    INDEX
    Explanations

    counting/fixing/identifying quantities

    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
    çİ°éĺ¶æ®µ
    -0.08
    èݺ
    -0.08
    avera
    -0.07
    çĶ¨æĦı
    -0.07
    å°±è¿ij
    -0.07
    yant
    -0.07
    ugno
    -0.07
    ikut
    -0.07
    igr
    -0.07
     Zit
    -0.07
    POSITIVE LOGITS
     counted
    0.08
     mues
    0.07
    _FIX
    0.07
     unique
    0.07
     uniquely
    0.07
    /stats
    0.07
    èįĨå·ŀ
    0.06
     contabil
    0.06
    fix
    0.06
    Fix
    0.06
    Activations Density 0.003%

    No Known Activations