© 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. 22238
    Prev
    Next
    INDEX
    Explanations

    second derivative of

    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
    bers
    -0.06
     valor
    -0.06
    BRE
    -0.05
    ارÙģ
    -0.05
    ember
    -0.05
    antas
    -0.05
     tac
    -0.05
    å¤ľ
    -0.05
     dil
    -0.05
    bre
    -0.05
    POSITIVE LOGITS
    ruh
    0.07
     nug
    0.06
    zÄĥ
    0.06
    uckle
    0.06
    resta
    0.06
    天åºŃ
    0.06
    æĽ²
    0.06
     zy
    0.06
    zy
    0.06
    ttes
    0.06
    Activations Density 0.048%

    No Known Activations