© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18798
    Prev
    Next
    INDEX
    Explanations

    continues to be

    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
     sức
    -0.07
    nya
    -0.06
    延å±ķ
    -0.06
    coln
    -0.06
    à¹ģà¸ģà¹Ī
    -0.06
    æ°Ĺãģ«åħ¥ãĤĬãģ®
    -0.06
    å¸Ĥæĸ°
    -0.06
    åĪ°æĸ°
    -0.06
    arrison
    -0.06
    ovem
    -0.06
    POSITIVE LOGITS
    ä»įæľª
    0.06
    ä»įæĺ¯
    0.06
    ä»į
    0.05
    oba
    0.05
    ä»įæľī
    0.05
     despite
    0.05
    ä¸į管
    0.05
     unequiv
    0.05
    åľ¨æľª
    0.05
     regardless
    0.05
    Activations Density 0.052%

    No Known Activations