© 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. 21524
    Prev
    Next
    INDEX
    Explanations

    and G

    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
    åĭĿ
    -0.06
    ÑĩаÑĤки
    -0.06
    彫
    -0.06
    槽
    -0.06
    _modify
    -0.06
    uell
    -0.06
    形形èī²
    -0.06
    ÑĢезÑĭ
    -0.06
     KHO
    -0.06
     naro
    -0.06
    POSITIVE LOGITS
    arach
    0.05
     intermediate
    0.05
     verdade
    0.05
     extrad
    0.05
    åı£
    0.05
     Morr
    0.05
    âij
    0.05
     main
    0.05
     Pistol
    0.05
     debut
    0.04
    Activations Density 0.036%

    No Known Activations