© 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. 17305
    Prev
    Next
    INDEX
    Explanations

    approximation and functional theory

    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
    å®
    -0.05
    åĪ»éª¨
    -0.05
    ä½ıæĪ¿åŁİ乡建设
    -0.05
    å¹¿æ³ĽçĶ¨äºİ
    -0.05
    own
    -0.05
     Ing
    -0.05
     Nap
    -0.05
    arrant
    -0.05
    land
    -0.05
    ovor
    -0.05
    POSITIVE LOGITS
    tent
    0.07
    æĦıè¦ĭ
    0.06
    iele
    0.06
    коÑģ
    0.06
     tent
    0.06
     conscient
    0.06
     Opinion
    0.06
    _leaf
    0.06
    妥
    0.06
     íĹĪ
    0.06
    Activations Density 0.011%

    No Known Activations