© 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. 21657
    Prev
    Next
    INDEX
    Explanations

    way to

    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
    æĸ¹å¼ıæĿ¥
    -0.06
     way
    -0.06
    ième
    -0.06
    åħ¶ä»ĸæĸ¹å¼ı
    -0.06
    ä½Ĩè¿Ļç§į
    -0.06
    è¿ģ
    -0.06
    acher
    -0.06
    åħ¼
    -0.06
    èĥ½
    -0.05
    jev
    -0.05
    POSITIVE LOGITS
     presence
    0.06
     h
    0.06
    qry
    0.05
    vas
    0.05
    illas
    0.05
    大æĶ¾
    0.05
     hô
    0.05
    illa
    0.05
    åħ¶äºº
    0.05
    箩
    0.05
    Activations Density 0.011%

    No Known Activations