© 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. 17712
    Prev
    Next
    INDEX
    Explanations

    sender EventArgs

    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
     rig
    -0.05
    çIJĨ
    -0.05
     controlled
    -0.05
     order
    -0.05
     *
    -0.05
    ire
    -0.05
    æĶ
    -0.05
     Order
    -0.05
    延
    -0.05
    *
    -0.05
    POSITIVE LOGITS
    pul
    0.07
    uyên
    0.07
    eli
    0.07
     bela
    0.06
    icale
    0.06
     fundos
    0.06
    ä¸įçĶ¨åĨį
    0.06
    icca
    0.06
    ÑĥÑĢе
    0.06
     ХабаÑĢ
    0.06
    Activations Density 0.029%

    No Known Activations