© 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. 3383
    Prev
    Next
    INDEX
    Explanations

    count, total, record, sum

    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
    ibe
    -0.07
    ãģĦãĤį
    -0.07
     Lazar
    -0.06
    Ren
    -0.06
    uka
    -0.06
    强弱
    -0.06
    è¡¡
    -0.06
    çİĩåħĪ
    -0.06
    å·²æĪIJ为
    -0.06
    L
    -0.06
    POSITIVE LOGITS
    agged
    0.08
     totals
    0.08
     sum
    0.07
    è®°å½ķ
    0.07
    åħŃ个
    0.07
    record
    0.07
    records
    0.07
     Anzahl
    0.07
     Welfare
    0.07
    æĢ»æķ°
    0.07
    Activations Density 0.002%

    No Known Activations