© 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. 17811
    Prev
    Next
    INDEX
    Explanations

    text following punctuation

    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
    ↵↵
    -0.07
    s
    -0.06
    Âł
    -0.06
    :
    -0.06
     (
    -0.05
    [
    -0.05
    ...
    -0.05
     ing
    -0.05
     da
    -0.05
    POSITIVE LOGITS
    illers
    0.08
    çģ«çĤ¬
    0.08
     !"
    0.07
    æĻĸ
    0.07
     obdob
    0.07
    tiers
    0.07
    вÑıÑĤÑģÑı
    0.07
     Caranya
    0.07
     )"
    0.07
    为äºĨ解åĨ³
    0.07
    Activations Density 0.001%

    No Known Activations