© 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. 17570
    Prev
    Next
    INDEX
    Explanations

    victory and its outcomes

    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
    emaan
    -0.07
    oved
    -0.07
    ly
    -0.07
    akaran
    -0.06
    گراÙĨ
    -0.06
    åĻ¨çļĦ
    -0.06
    çĵľ
    -0.06
    ocked
    -0.06
    åĪ°èĻķ
    -0.06
    /up
    -0.06
    POSITIVE LOGITS
    è«ĩ
    0.05
    éĩĮäºļ
    0.05
    ivity
    0.05
    é£İæ³¢
    0.05
    angkan
    0.05
    etas
    0.05
    igar
    0.05
    eh
    0.05
    ea
    0.05
     winds
    0.05
    Activations Density 0.009%

    No Known Activations