© 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. 17544
    Prev
    Next
    INDEX
    Explanations

    throat

    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
    اÙĦات
    -0.06
    çļĦ大èĦij
    -0.06
    ðŁĻĤ
    -0.06
    etros
    -0.06
    etra
    -0.06
    ENN
    -0.06
    ukum
    -0.06
    SYM
    -0.06
    dater
    -0.06
    åݨåį«
    -0.06
    POSITIVE LOGITS
     throat
    0.06
    oub
    0.05
    à¹ĥย
    0.05
    åĸī
    0.05
     desn
    0.05
     doubt
    0.05
    дÑĢоб
    0.05
     Meat
    0.05
     garg
    0.05
    icity
    0.05
    Activations Density 0.012%

    No Known Activations