© 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. 17883
    Prev
    Next
    INDEX
    Explanations

    fabric

    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
    ever
    -0.06
    iggins
    -0.06
    inton
    -0.05
    ed
    -0.05
    ie
    -0.05
    els
    -0.05
    ens
    -0.05
     دادÙĨ
    -0.05
    ged
    -0.05
    ãģĿãģĵãģ«
    -0.05
    POSITIVE LOGITS
    ÑģлÑĮ
    0.09
    ordial
    0.08
    apore
    0.08
    éħĴå±ĭ
    0.08
     cherchez
    0.08
    æĸ°åĬłåĿ¡
    0.08
    sprecher
    0.07
    izations
    0.07
    isations
    0.07
    arily
    0.07
    Activations Density 0.012%

    No Known Activations