© 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. 18148
    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
    velopp
    -0.06
    æĬĬæĪij们
    -0.06
    kena
    -0.06
    jours
    -0.06
    ãĤ·ãĥ¼
    -0.06
    è§ģäºĨ
    -0.06
    å¦ĤåĽ¾
    -0.06
    ibat
    -0.06
    çļĦåĪ¶ä½ľæĸ¹æ³ķ
    -0.06
    çĿĢæĪij们
    -0.06
    POSITIVE LOGITS
    sh
    0.05
    napshot
    0.05
    agger
    0.05
    ìľł
    0.05
     swear
    0.05
     precise
    0.05
    tr
    0.05
     ìľł
    0.05
    Fore
    0.05
    ub
    0.04
    Activations Density 0.000%

    No Known Activations