© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19893
    Prev
    Next
    INDEX
    Explanations

    xml tag metadata

    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
    ürg
    -0.06
    Signature
    -0.05
    à¸Ħร
    -0.05
    ÙĪÙħÙĬ
    -0.05
    ç»Ī
    -0.05
    weite
    -0.05
    влении
    -0.05
    ä¾Ľæ°Ķ
    -0.05
     СеÑĢге
    -0.05
    ilh
    -0.05
    POSITIVE LOGITS
    ambu
    0.06
    Houston
    0.06
    laubt
    0.06
     disarm
    0.06
    akis
    0.05
    unter
    0.05
    è®°å¿Ĩä¸Ń
    0.05
    é«ĺ级工ç¨ĭå¸Ī
    0.05
     Pod
    0.05
    åģ¥åº·å®īåħ¨
    0.05
    Activations Density 0.001%

    No Known Activations