© 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. 18365
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    emor
    -0.06
    ÑĢок
    -0.06
    æ¤Ĵ
    -0.06
    aret
    -0.06
    miot
    -0.05
    umer
    -0.05
    oare
    -0.05
     numbers
    -0.05
    मà¥ĩà¤Ĥ
    -0.05
    शा
    -0.05
    POSITIVE LOGITS
     supl
    0.06
     des
    0.06
    ا
    0.06
    æľīéľĢè¦ģ
    0.06
     supplement
    0.05
    bre
    0.05
     panc
    0.05
     Supplement
    0.05
     ÙĪاÙĦسÙĦاÙħ
    0.05
    ç¼ĵ
    0.05
    Activations Density 0.000%

    No Known Activations