© 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. 22091
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
    åħ·
    -0.06
    ello
    -0.05
    aine
    -0.05
    ìłIJìĹIJ
    -0.05
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.05
    家æĿij
    -0.05
    iem
    -0.05
    æĸĩåĮĸä¼łæĴŃæľīéĻIJåħ¬åı¸
    -0.05
    /all
    -0.05
    ïque
    -0.05
    POSITIVE LOGITS
    Ø·
    0.06
    驶åħ¥
    0.06
    çģ«çĥ§
    0.06
    å§Ĺ
    0.05
    lauf
    0.05
    ÑĢÑı
    0.05
    èĥ½æĪIJ为
    0.05
    æݪ
    0.05
    appoint
    0.05
    commit
    0.05
    Activations Density 0.013%

    No Known Activations