© 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. 47418
    Prev
    Next
    INDEX
    Explanations

    convergence, divergence, properties, results

    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
    entifier
    -0.07
    à¸ģำà¹Ģà¸Ļิà¸Ķ
    -0.07
    fully
    -0.07
    aker
    -0.06
    oret
    -0.06
     Ñģобой
    -0.06
    acz
    -0.06
    tery
    -0.06
    wards
    -0.06
    ä¼ļåIJĮ
    -0.06
    POSITIVE LOGITS
    oglio
    0.11
    edor
    0.10
    ezza
    0.10
    LBL
    0.09
    isseur
    0.09
    สูà¹Ī
    0.08
    heels
    0.08
    emente
    0.08
    aison
    0.08
    esto
    0.08
    Activations Density 0.005%

    No Known Activations