© 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. 17758
    Prev
    Next
    INDEX
    Explanations

    search and discover

    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
    ta
    -0.06
    æĺİ
    -0.05
    f
    -0.05
    å®Įç¾İ
    -0.05
    verein
    -0.05
    اط
    -0.05
    æĸ¹æĸ¹éĿ¢
    -0.05
    ew
    -0.05
    ivo
    -0.05
    enton
    -0.05
    POSITIVE LOGITS
    åħ°çī¹
    0.07
    ëŀij
    0.06
    اÙĨÛĮ
    0.06
    trys
    0.06
     Klos
    0.06
    æµ·åĮº
    0.06
     ãĤıãģĭãĤīãģªãģĦ
    0.06
     întâl
    0.06
    .googleapis
    0.06
    å¼ĢéĺĶ
    0.06
    Activations Density 0.012%

    No Known Activations