© 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. 18133
    Prev
    Next
    INDEX
    Explanations

    amine groups

    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
    åIJĦ个
    -0.06
    rens
    -0.05
    менÑĥ
    -0.05
    åĩŃ空
    -0.05
    åĿļä¿¡
    -0.05
    rira
    -0.05
    ukum
    -0.05
    jala
    -0.05
     Merdeka
    -0.05
    uchu
    -0.05
    POSITIVE LOGITS
    åĪ©
    0.06
    mine
    0.05
    parte
    0.05
    客
    0.05
    лади
    0.05
     parte
    0.05
    å°ıåŀĭ
    0.05
    ç©¿æĪ´
    0.05
     dup
    0.05
     Fork
    0.05
    Activations Density 0.015%

    No Known Activations