© 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. 17415
    Prev
    Next
    INDEX
    Explanations

    .getChildAt

    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
     major
    -0.05
    以æѤ
    -0.05
    -0.05
    (
    -0.05
    ł
    -0.05
    “
    -0.04
    =
    -0.04
     -
    -0.04
     Ñģобой
    -0.04
    ,
    -0.04
    POSITIVE LOGITS
     rued
    0.07
     Pue
    0.07
    olet
    0.07
    istr
    0.07
     alist
    0.07
    illante
    0.07
     recons
    0.07
    oline
    0.07
    ÑīноÑģÑĤÑĮ
    0.06
    istentes
    0.06
    Activations Density 0.004%

    No Known Activations