© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18465
    Prev
    Next
    INDEX
    Explanations

    programming result assignment

    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
    гÑĢад
    -0.05
    åĮ¿åIJįçĶ¨æĪ·
    -0.05
    å¶
    -0.05
    æĦıèŃĺ
    -0.05
    min
    -0.05
    å²Ń
    -0.05
    armac
    -0.05
    graded
    -0.05
    æĪIJ績
    -0.05
    çݩ家们
    -0.05
    POSITIVE LOGITS
    orate
    0.06
    оÑĩно
    0.06
    ãģ»ãģĨ
    0.06
    fid
    0.06
    èħ¹
    0.06
    aland
    0.06
    itas
    0.06
    utter
    0.06
    igate
    0.06
    urch
    0.06
    Activations Density 0.015%

    No Known Activations