© 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. 17881
    Prev
    Next
    INDEX
    Explanations

    depicting or portraying

    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
    itÃł
    -0.06
     thôi
    -0.06
    later
    -0.06
    erer
    -0.06
    ités
    -0.05
    æĢ§çĸ¾çĹħ
    -0.05
    бÑĢÑı
    -0.05
    åijµåijµ
    -0.05
    çŁ¥çļĦ
    -0.05
    ear
    -0.05
    POSITIVE LOGITS
    à¹Ħหรà¹Ī
    0.08
    untura
    0.06
     bunch
    0.06
    ango
    0.06
     Nobody
    0.06
    ëŁ¼
    0.06
     Neuroscience
    0.06
    ized
    0.06
     Incredible
    0.06
    ember
    0.06
    Activations Density 0.006%

    No Known Activations