© 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. 21252
    Prev
    Next
    INDEX
    Explanations

    willing to

    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
    Ø©
    -0.07
    ular
    -0.06
    Ñĭ
    -0.06
    Ñĥ
    -0.06
    urope
    -0.06
    s
    -0.06
    ÙĬØ©
    -0.05
    หมูà¹Ī
    -0.05
     latter
    -0.05
    ishes
    -0.05
    POSITIVE LOGITS
    tien
    0.07
    ez
    0.07
    деб
    0.06
    ands
    0.06
    ÙĩÛĮ
    0.06
    его
    0.06
    ptom
    0.06
    or
    0.06
    eb
    0.06
    esk
    0.06
    Activations Density 0.001%

    No Known Activations