© 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. 42386
    Prev
    Next
    INDEX
    Explanations

    tone

    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
    ories
    -0.11
    èĢĮå¦Ĥä»Ĭ
    -0.08
    аÑİÑĤ
    -0.08
    Ø©
    -0.07
    бÑĥдÑĮÑĤе
    -0.07
    ignment
    -0.07
    ness
    -0.07
    одно
    -0.07
    OperationException
    -0.07
    åħĭ森
    -0.07
    POSITIVE LOGITS
    ancier
    0.10
    less
    0.09
    ality
    0.08
    yssey
    0.08
    ر
    0.08
    راد
    0.08
    à§įড
    0.08
    richter
    0.08
    meric
    0.08
    ienz
    0.08
    Activations Density 0.033%

    No Known Activations