© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18623
    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
    害
    -0.07
    æľĪèĩ³ä»Ĭ
    -0.05
    åħ¨ä¹¦
    -0.05
    éĥ½ä¸įæĥ³
    -0.05
    éĽį
    -0.05
    -and
    -0.05
    komm
    -0.05
    èĬ±æŀľ
    -0.05
    ÑĢаÑĤно
    -0.05
    åİĭåĬĽå¤§
    -0.05
    POSITIVE LOGITS
    ight
    0.06
    çħ§
    0.06
    ht
    0.06
    flt
    0.06
    dess
    0.06
    icht
    0.05
    åIJįçĤº
    0.05
    dia
    0.05
    edi
    0.05
    alang
    0.05
    Activations Density 0.000%

    No Known Activations