© 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. 21736
    Prev
    Next
    INDEX
    Explanations

    since followed by a time period

    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
    istant
    -0.07
    ÑĪе
    -0.06
    wart
    -0.06
    ally
    -0.06
    æĹłéĻIJ
    -0.05
    otion
    -0.05
    ibilmente
    -0.05
    æĢ§æ¬²
    -0.05
    izard
    -0.05
    ä¸įèĥľ
    -0.05
    POSITIVE LOGITS
    å¹³åİŁ
    0.06
    æ¡Ī
    0.06
    edr
    0.06
    plings
    0.06
    è§ģåºķ
    0.06
    RAL
    0.06
    å¾·åĪ©
    0.05
    ÑĢенд
    0.05
    anen
    0.05
    é¢ĺ
    0.05
    Activations Density 0.026%

    No Known Activations