© 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. 18346
    Prev
    Next
    INDEX
    Explanations

    gaming industry and consoles

    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
    ÅĤad
    -0.06
    nyata
    -0.06
    ç»Ħç»Ħéķ¿
    -0.06
    tica
    -0.06
    enda
    -0.06
    mite
    -0.06
    echt
    -0.06
    hn
    -0.06
    .prototype
    -0.06
    绢
    -0.06
    POSITIVE LOGITS
    ise
    0.06
    i
    0.06
    ied
    0.05
    æĹ¢
    0.05
    æŁĵ
    0.05
    imports
    0.05
    urge
    0.05
    å½Ŀ
    0.05
    æĮij
    0.05
    ERI
    0.05
    Activations Density 0.008%

    No Known Activations