© 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. 17740
    Prev
    Next
    INDEX
    Explanations

    us company processor Apple players

    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
    åIJįåı«
    -0.07
    izr
    -0.07
    个好
    -0.07
    æģº
    -0.07
    گز
    -0.06
    cep
    -0.06
    ampo
    -0.06
    vaard
    -0.06
    ichtet
    -0.06
     Keystone
    -0.06
    POSITIVE LOGITS
    AY
    0.05
     perdana
    0.05
    åĪĨéĺŁ
    0.05
     bè
    0.05
     hy
    0.05
    奥åĪ©
    0.05
    pres
    0.05
     ÑģÑĤоÑĢон
    0.05
     विश
    0.04
     appearances
    0.04
    Activations Density 0.012%

    No Known Activations