© 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. 18178
    Prev
    Next
    INDEX
    Explanations

    self followed by words

    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
    indest
    -0.06
     bénévoles
    -0.06
    ä¹ĭå®Ŀ
    -0.06
    wards
    -0.06
    luš
    -0.06
    äºijéĽĨ
    -0.06
    çķĮ线
    -0.06
    hire
    -0.06
    Opened
    -0.06
    amedi
    -0.06
    POSITIVE LOGITS
    iveness
    0.07
    t
    0.07
    羣æŃ£çļĦ
    0.06
    raz
    0.05
    ÑģÑĤв
    0.05
    g
    0.05
    te
    0.05
    eld
    0.05
    T
    0.05
    omin
    0.05
    Activations Density 0.013%

    No Known Activations