© 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. 17295
    Prev
    Next
    INDEX
    Explanations

    guessing and thinking

    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
    azer
    -0.07
    ุ
    -0.07
     vini
    -0.07
    é¢IJ
    -0.07
    ennes
    -0.06
    éªĦ
    -0.06
    çĤ¯
    -0.06
    undef
    -0.06
    Ùģات
    -0.06
     prestación
    -0.06
    POSITIVE LOGITS
    اÙĨÙĩ
    0.05
    ster
    0.05
    çīºçī²
    0.05
     conce
    0.05
    éĻ¤
    0.05
    éĶ¥
    0.05
     vom
    0.05
     organ
    0.04
    ç»´åŁºçĻ¾ç§ij
    0.04
    èģĶæĥ³åĪ°
    0.04
    Activations Density 0.618%

    No Known Activations