© 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. 17993
    Prev
    Next
    INDEX
    Explanations

    .com/

    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
    ẻ
    -0.07
    alism
    -0.06
    edal
    -0.06
    Leist
    -0.06
    å¾Ĺ天çĭ¬
    -0.06
    çİ°å®ŀæĦıä¹ī
    -0.06
    ørs
    -0.06
    lük
    -0.06
     véhic
    -0.06
    orum
    -0.06
    POSITIVE LOGITS
    elt
    0.06
     pe
    0.05
    {
    0.05
    æľ«
    0.05
    æī°
    0.05
    ail
    0.05
     som
    0.05
    æĮīçħ§
    0.05
    AC
    0.04
    -pe
    0.04
    Activations Density 0.002%

    No Known Activations