© 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. 18254
    Prev
    Next
    INDEX
    Explanations

    podcast

    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
     inst
    -0.06
     w
    -0.05
    istory
    -0.05
    åħ¶åľ¨
    -0.05
    fu
    -0.05
    lob
    -0.05
    ational
    -0.05
    ilinear
    -0.05
    /
    -0.04
    uos
    -0.04
    POSITIVE LOGITS
    ï¸İ
    0.07
    пиÑĤ
    0.07
    plik
    0.07
    volmente
    0.06
    è½
    0.06
    toral
    0.06
    æŀķ
    0.06
    ï¸ı
    0.06
    влека
    0.06
    ruptcy
    0.06
    Activations Density 0.016%

    No Known Activations