© 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. 27028
    Prev
    Next
    INDEX
    Explanations

    part 1, part 2, part 3

    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
    iras
    -0.09
    ä¸ĢéĹª
    -0.08
    ouri
    -0.08
    atika
    -0.07
    enner
    -0.07
    оÑĢод
    -0.07
    ä¿±è¿Ľ
    -0.07
    cience
    -0.07
    olean
    -0.07
    ecin
    -0.07
    POSITIVE LOGITS
     part
    0.10
     Part
    0.09
    part
    0.08
     parte
    0.08
    第äºĮéĥ¨åĪĨ
    0.08
    Part
    0.08
     czÄĻÅĽÄĩ
    0.08
     deel
    0.08
     continued
    0.08
    å¸ĸ
    0.08
    Activations Density 0.400%

    No Known Activations