© 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. 21793
    Prev
    Next
    INDEX
    Explanations

    website metadata

    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
    åŁºç¡Ģ
    -0.06
     eng
    -0.05
    èĤ©
    -0.05
    éb
    -0.05
    çļĦåŁºç¡Ģ
    -0.05
    èģĶæľº
    -0.05
    æĹ¥
    -0.05
    ophobic
    -0.05
    çĦī
    -0.05
     nob
    -0.05
    POSITIVE LOGITS
     rado
    0.07
    LOOD
    0.06
    åĽ½åĬ¡éĻ¢åħ³äºİ
    0.06
    æĭ¥æľī丰å¯ĮçļĦ
    0.06
     تÙĨا
    0.06
    åħ·æľī丰å¯ĮçļĦ
    0.06
     concord
    0.06
    à¸Ĺัà¹Īà¸§à¸Ľà¸£à¸°à¹Ģà¸Ĺศ
    0.06
    çĩİ
    0.06
    hya
    0.05
    Activations Density 0.004%

    No Known Activations