© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18007
    Prev
    Next
    INDEX
    Explanations

    manifold geometry metric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    审
    -0.06
    çĨĶæĸŃ
    -0.05
    bins
    -0.05
     пÑĢим
    -0.05
    審
    -0.05
    çĪµ
    -0.05
    çī¹åĪ«
    -0.05
     rem
    -0.05
    åľ¨ç¾İ
    -0.05
    rem
    -0.05
    POSITIVE LOGITS
    umann
    0.06
    atholic
    0.06
    ÐĵлавнÑĭе
    0.06
    åħ¨å¤©åĢĻ
    0.06
     patches
    0.06
    åĪĪ
    0.06
     palms
    0.06
    umbed
    0.06
    دÙĬات
    0.06
    à¸ŀà¸ĩ
    0.06
    Activations Density 0.049%

    No Known Activations