© 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. 10931
    Prev
    Next
    INDEX
    Explanations

    porphyrin

    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
    iffe
    -0.07
    ewn
    -0.07
    opp
    -0.07
    æ²³å¸Ĥ
    -0.07
    ition
    -0.07
     litt
    -0.07
    ç¥Ł
    -0.06
    缴è§Ĵ
    -0.06
    æľĢç»ĪåıĹçĽĬ
    -0.06
    çĴIJ
    -0.06
    POSITIVE LOGITS
    cak
    0.08
    è¡Ģ红
    0.08
    çĮªèĤĿ
    0.08
     Fech
    0.07
     precursor
    0.07
    大红
    0.07
    azan
    0.07
    azen
    0.07
    chnet
    0.07
    Milliseconds
    0.07
    Activations Density 0.107%

    No Known Activations