© 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. 56299
    Prev
    Next
    INDEX
    Explanations

    characters or part

    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
    iless
    -0.07
    ÑĢои
    -0.07
    acre
    -0.07
    igy
    -0.07
    kee
    -0.07
    atamente
    -0.07
    urge
    -0.07
    产
    -0.07
    곡
    -0.07
    åľĥ
    -0.07
    POSITIVE LOGITS
    åĽłä¸ºåľ¨
    0.12
     because
    0.12
    åĽłä¸º
    0.11
    because
    0.11
    åĽłçĤº
    0.10
     since
    0.10
    åĽłä¸ºæĪij
    0.10
    åĽłä¸ºåħ¶
    0.10
    åĽłä¸ºä½ł
    0.09
    åĽłä¸ºå®ĥ
    0.09
    Activations Density 0.034%

    No Known Activations