© 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. 23990
    Prev
    Next
    INDEX
    Explanations

    html artifact ids

    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
    äge
    -0.08
    atika
    -0.07
    ÄĻd
    -0.07
    ÈĻa
    -0.07
    éłĵ
    -0.07
    empla
    -0.07
    ono
    -0.07
    anks
    -0.07
    aç
    -0.07
    anked
    -0.07
    POSITIVE LOGITS
    åİļæľĽ
    0.07
    oint
    0.07
    ieten
    0.06
    次åħĥ
    0.06
    Į
    0.06
    ervations
    0.06
    енÑĤ
    0.06
    ¦
    0.06
    æ¯Ľæ³½ä¸ľ
    0.06
    averse
    0.06
    Activations Density 0.009%

    No Known Activations