© 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. 14081
    Prev
    Next
    INDEX
    Explanations

    ray geometry, ray trace, ray caster

    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
    imers
    -0.08
    zza
    -0.07
     slags
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    erland
    -0.07
     Aires
    -0.07
    annabin
    -0.07
    hips
    -0.07
     esfuer
    -0.07
    ãģŁãĤģ
    -0.07
    POSITIVE LOGITS
    ยà¸Ļà¸ķà¹Į
    0.09
    leigh
    0.09
    à¹Ģà¸Ľà¸¥à¹Īา
    0.08
    /column
    0.08
    iness
    0.08
    纷åijĪ
    0.08
    theon
    0.08
    onnement
    0.08
    folge
    0.07
    коÑģÑĤÑĮ
    0.07
    Activations Density 0.010%

    No Known Activations