© 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. 22223
    Prev
    Next
    INDEX
    Explanations

    love and relationships

    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
    æĹ¢çĦ¶
    -0.06
    Present
    -0.06
    elj
    -0.06
     Leisure
    -0.05
    iés
    -0.05
    present
    -0.05
    ideo
    -0.05
    chau
    -0.05
    åıįåĬ¨
    -0.05
    vene
    -0.05
    POSITIVE LOGITS
    éĶ¦ä¸Ĭæ·»èĬ±
    0.06
     otherwise
    0.06
    nC
    0.05
    è¦ģä¸įçĦ¶
    0.05
    ijn
    0.05
     typical
    0.05
    人éĹ´
    0.05
    tc
    0.05
    зал
    0.05
     sp
    0.05
    Activations Density 0.008%

    No Known Activations