© 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. 21540
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    æĥ¹
    -0.07
    éķ¿èħ¿
    -0.06
    imilar
    -0.06
    oro
    -0.06
    wirtschaft
    -0.06
    haust
    -0.05
    entifier
    -0.05
    ores
    -0.05
    ortic
    -0.05
    -blood
    -0.05
    POSITIVE LOGITS
    langs
    0.06
    amah
    0.05
    çªį
    0.05
    amos
    0.05
     Phá»iji
    0.05
    夫
    0.05
    Ö·
    0.05
    ekk
    0.05
     Fak
    0.05
    æ¶ī
    0.05
    Activations Density 0.004%

    No Known Activations