© 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. 17628
    Prev
    Next
    INDEX
    Explanations

    orbit paths

    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
    -hearted
    -0.06
    æ¶Ł
    -0.06
    ify
    -0.06
    istente
    -0.06
    åıĬåħ¶èĩªåĬ¨åĮĸ
    -0.06
    ness
    -0.06
    ogne
    -0.06
    Enough
    -0.06
    stown
    -0.05
    olim
    -0.05
    POSITIVE LOGITS
    cul
    0.06
    alement
    0.06
    moid
    0.06
    lick
    0.06
    TING
    0.05
    اث
    0.05
    icle
    0.05
    iding
    0.05
    nal
    0.05
    ally
    0.05
    Activations Density 0.004%

    No Known Activations