© 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. 14316
    Prev
    Next
    INDEX
    Explanations

    bulk material properties

    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
    earch
    -0.08
    hips
    -0.08
    ãi
    -0.08
    aries
    -0.07
    zelf
    -0.07
     szól
    -0.07
    éģĹçĹĩ
    -0.07
     vặt
    -0.07
    à¹Ħà¸Ĥ
    -0.07
    achts
    -0.07
    POSITIVE LOGITS
    uri
    0.08
    ue
    0.08
    imately
    0.08
    cular
    0.08
    ers
    0.08
    ier
    0.08
    ument
    0.08
    rave
    0.08
    iness
    0.07
    rary
    0.07
    Activations Density 0.021%

    No Known Activations