© 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. 17181
    Prev
    Next
    INDEX
    Explanations

    supervision

    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
    ainer
    -0.08
    asters
    -0.07
    EMPL
    -0.06
    åħ¶æŀĹ
    -0.06
    æĹıèĩªæ²»
    -0.06
    æĹıèĩªæ²»åİ¿
    -0.06
    çĭ¬çĶŁåŃIJ女
    -0.06
    ton
    -0.06
    sworth
    -0.06
    opp
    -0.06
    POSITIVE LOGITS
    esh
    0.06
    μÏīÏĤ
    0.06
    æł¹æį®éľĢè¦ģ
    0.06
    felt
    0.06
    ãģŁãĤĭ
    0.05
     olev
    0.05
    новÑĮ
    0.05
    eded
    0.05
    æīĢ称
    0.05
    iw
    0.05
    Activations Density 0.009%

    No Known Activations