© 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. 17774
    Prev
    Next
    INDEX
    Explanations

    Kristen Stewart

    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
    ...',
    -0.07
    dap
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    ÂŃs
    -0.07
    woord
    -0.06
    表达èĥ½åĬĽ
    -0.06
    çĮĽè¿Ľ
    -0.06
    缸è¾ħ缸æĪIJ
    -0.06
    shed
    -0.06
    $o
    -0.06
    POSITIVE LOGITS
    icate
    0.06
    ans
    0.05
    un
    0.05
    eka
    0.05
    -un
    0.05
    èĢģç¥ĸ
    0.05
    th
    0.05
     Un
    0.05
    aines
    0.05
    æĭŁ
    0.05
    Activations Density 0.004%

    No Known Activations