© 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. 21819
    Prev
    Next
    INDEX
    Explanations

    woke up

    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
    ly
    -0.07
    èĩªå·±
    -0.06
    oriously
    -0.06
    éĻĦè¿ijæľī
    -0.06
    ä¹İ
    -0.06
    odore
    -0.05
    forth
    -0.05
    ÄĽÅ¾
    -0.05
    ạm
    -0.05
    qui
    -0.05
    POSITIVE LOGITS
    家çļĦ
    0.07
    åħ¥éĩij
    0.05
    ä¸ĭæĶ¾
    0.05
    éĶ¨
    0.05
    informatics
    0.05
    bla
    0.05
    æ°¨éħ¸
    0.05
    JU
    0.05
    RTL
    0.05
     boca
    0.05
    Activations Density 0.003%

    No Known Activations