© 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. 21173
    Prev
    Next
    INDEX
    Explanations

    computing and technical terms

    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
    éĨį
    -0.06
    ysin
    -0.06
    aruhi
    -0.06
    åIJijåħ¶
    -0.06
    åıĹåĪ°å½±åĵį
    -0.06
    omie
    -0.06
    æĸ¤
    -0.05
    uscht
    -0.05
    inasikan
    -0.05
    éĿ¢çĽ®
    -0.05
    POSITIVE LOGITS
    fan
    0.06
    ष
    0.05
     embedded
    0.05
     Embedded
    0.05
    åĿª
    0.05
    utra
    0.05
    erad
    0.05
    andet
    0.05
    azol
    0.05
    f
    0.05
    Activations Density 0.051%

    No Known Activations