© 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. 17424
    Prev
    Next
    INDEX
    Explanations

    classification or network structures

    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
     Hint
    -0.06
    soc
    -0.06
    溶åīĤ
    -0.06
    ØŃÙĬØ©
    -0.05
    wod
    -0.05
    éry
    -0.05
    estina
    -0.05
    çľ¼çº¿
    -0.05
    ERO
    -0.05
     solver
    -0.05
    POSITIVE LOGITS
    urse
    0.06
    注åĨĮèµĦæľ¬ä¸º
    0.06
    æĹºçĽĽ
    0.06
    颤æĬĸ
    0.05
    ç³»çļĦ
    0.05
    rosse
    0.05
    å¾ĭ
    0.05
    æ´²éĻħ
    0.05
     {}:
    0.05
    anson
    0.05
    Activations Density 0.001%

    No Known Activations