© 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. 17669
    Prev
    Next
    INDEX
    Explanations

    pathology, practice, disorder, apoptosis

    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
    еÑĨ
    -0.06
    enced
    -0.05
    rente
    -0.05
    继
    -0.05
    ERIC
    -0.05
    qv
    -0.05
    ÑĨ
    -0.05
    VID
    -0.05
     Wouldn
    -0.05
    å¼Ĥ
    -0.05
    POSITIVE LOGITS
    è·ŁèijĹ
    0.05
    ä¿±è¿Ľ
    0.05
    iro
    0.05
    åľ¨å¾®åįļ
    0.05
    æŀģ强çļĦ
    0.05
     uda
    0.05
    没åħ³ç³»
    0.05
    nagyobb
    0.05
    è·ŁæĪij们
    0.05
    isestä
    0.05
    Activations Density 0.114%

    No Known Activations