© 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. 23919
    Prev
    Next
    INDEX
    Explanations

    more details

    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
    eref
    -0.08
    rip
    -0.08
    пелÑĮ
    -0.08
    anf
    -0.08
    гоÑĤо
    -0.08
    zg
    -0.07
    upo
    -0.07
    gni
    -0.07
    ä¸Ģ鸣
    -0.07
    ade
    -0.07
    POSITIVE LOGITS
    eny
    0.07
     Kreuz
    0.06
     flank
    0.05
    mitters
    0.05
    被çĽĹ
    0.05
    tat
    0.05
    _filt
    0.05
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.05
     Ju
    0.05
     Fremd
    0.05
    Activations Density 0.395%

    No Known Activations