© 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. 21761
    Prev
    Next
    INDEX
    Explanations

    the following number

    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
    inda
    -0.06
    æīij
    -0.05
    ØŃÙģ
    -0.05
    åºĶç«ĭåį³
    -0.05
    IST
    -0.05
    istic
    -0.05
    sic
    -0.05
    ζε
    -0.05
    UGH
    -0.05
    uchtet
    -0.05
    POSITIVE LOGITS
    ünt
    0.06
    quisites
    0.06
    缨
    0.06
    ikken
    0.06
    èĨı
    0.05
    enne
    0.05
    ãĥĬãĥ¼
    0.05
    é»Ħä½ĵ
    0.05
    个çľģ
    0.05
    sert
    0.05
    Activations Density 0.001%

    No Known Activations