© 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. 55781
    Prev
    Next
    INDEX
    Explanations

    depalletizing/palletizing boxes

    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
    åķĬ
    -0.08
    —or
    -0.07
    ——
    -0.07
    —one
    -0.06
    erson
    -0.06
    bes
    -0.06
    —an
    -0.06
    —the
    -0.06
    ionato
    -0.06
    æĸ°æĺ¥
    -0.06
    POSITIVE LOGITS
    /etc
    0.18
    atre
    0.11
     combo
    0.09
    èĩªå·±
    0.09
    yre
    0.09
     combos
    0.08
    etre
    0.08
    ä¸Ģä½ĵæľº
    0.08
    /-
    0.08
    oir
    0.08
    Activations Density 0.141%

    No Known Activations