© 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. 17461
    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
     analogous
    -0.07
    ied
    -0.07
    ç±»æ¯Ķ
    -0.06
    acic
    -0.06
    iet
    -0.06
    SC
    -0.05
    same
    -0.05
    iel
    -0.05
     decidi
    -0.05
    bot
    -0.05
    POSITIVE LOGITS
    å¦ĤæŃĮ
    0.06
    ).-
    0.06
     xpos
    0.06
    eazÄĥ
    0.05
    uca
    0.05
    ç²±
    0.05
    lada
    0.05
    ITCH
    0.05
     поÑģ
    0.05
    oare
    0.05
    Activations Density 0.000%

    No Known Activations