© 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. 17957
    Prev
    Next
    INDEX
    Explanations

    encoded

    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
    æŃ¤ä¸º
    -0.06
    elow
    -0.06
    ä¸ĭ称
    -0.06
    èĩªå·±éĥ½
    -0.06
    evi
    -0.05
     позд
    -0.05
    æķ¬è¯·æľŁå¾ħ
    -0.05
    çĦ¡æ¯Ķ
    -0.05
    h
    -0.05
    ä¹Łæĺ¯åįģåĪĨ
    -0.05
    POSITIVE LOGITS
    ãģ£ãģ½
    0.06
    åľ¨è¿Ļ个è¿ĩç¨ĭä¸Ń
    0.06
    çĶļèĩ³åı¯ä»¥
    0.06
     really
    0.06
    æ¯ıä¸Ģ次
    0.06
     efect
    0.05
    ump
    0.05
    UBL
    0.05
    ç«ł
    0.05
    urm
    0.05
    Activations Density 0.117%

    No Known Activations