© 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. 57146
    Prev
    Next
    INDEX
    Explanations

    medical, geographical, and proper nouns

    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
    éľ
    -0.06
    etr
    -0.06
    éĸ
    -0.06
    -
    -0.06
    éĨ
    -0.06
     (
    -0.06
    à¸ĸ
    -0.06
    æ¾
    -0.06
     initially
    -0.05
    åĩłæ¬¡
    -0.05
    POSITIVE LOGITS
     sacco
    0.09
    áĥ¦
    0.08
    (es
    0.08
    riques
    0.08
    coes
    0.08
    mination
    0.08
    INAN
    0.08
    å¼Ģå¼Ģå¿ĥ
    0.07
    /es
    0.07
    _sidebar
    0.07
    Activations Density 0.035%

    No Known Activations