© 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. 22206
    Prev
    Next
    INDEX
    Explanations

    distinguish a, original educational

    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
    失败äºĨ
    -0.06
    Å¡Äį
    -0.06
    ืà¹Īà¸Ń
    -0.06
    ä¿¡çĶ¨ä¿¡æģ¯
    -0.05
    æľŁéĻIJ为
    -0.05
    ÙĪرÙĩا
    -0.05
    vä
    -0.05
    å±Ĩ
    -0.05
    tier
    -0.05
    å¤ļ大çļĦ
    -0.05
    POSITIVE LOGITS
    éģ¿åħįäºĨ
    0.06
     avoided
    0.06
    reeze
    0.06
    avoid
    0.06
    çŁ¥ä¹ĭ
    0.05
    oui
    0.05
    anky
    0.05
     transition
    0.05
    ç³»åĪĹ
    0.05
    åı¯ä»¥éģ¿åħį
    0.05
    Activations Density 0.005%

    No Known Activations