© 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. 17233
    Prev
    Next
    INDEX
    Explanations

    poor judgment, bad decisions, mistakes

    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
    burg
    -0.06
    ardy
    -0.06
    alis
    -0.06
    pond
    -0.06
    heit
    -0.06
    æ·¡å®ļ
    -0.06
    æĹ©çĤ¹
    -0.05
     robin
    -0.05
    åıĺæĢģ
    -0.05
    ès
    -0.05
    POSITIVE LOGITS
    è¨Ĺ
    0.06
    æīĺ
    0.06
    è¿IJ
    0.06
    éĢļ
    0.06
    èĪ¶
    0.05
    igest
    0.05
    éģĭ
    0.05
    еÑĩениÑı
    0.05
    éĽĨä¸Ń
    0.05
    akest
    0.05
    Activations Density 0.003%

    No Known Activations