© 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. 22079
    Prev
    Next
    INDEX
    Explanations

    years since

    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
    chand
    -0.06
    éĿ¢æĹłè¡¨æĥħ
    -0.06
    å®ģåı¯
    -0.05
    into
    -0.05
     academia
    -0.05
    astra
    -0.05
    ваÑĢ
    -0.05
    å¹²èĦĨ
    -0.05
     تر
    -0.05
    terÃł
    -0.05
    POSITIVE LOGITS
    ehend
    0.06
    ebab
    0.06
    illage
    0.06
    Äģv
    0.06
    شارات
    0.06
    ipped
    0.06
    å»ī
    0.05
    rame
    0.05
    heet
    0.05
    ä¸ļ
    0.05
    Activations Density 0.129%

    No Known Activations