© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20529
    Prev
    Next
    INDEX
    Explanations

    men's/women's clothing and sports

    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
    çĶµå¹³
    -0.06
    atap
    -0.06
    -eyed
    -0.06
    apun
    -0.06
    ä¸ªå·¥ä½ľ
    -0.05
    ëĶ¸
    -0.05
    andard
    -0.05
    ohn
    -0.05
    oon
    -0.05
     orale
    -0.05
    POSITIVE LOGITS
    otr
    0.05
    elm
    0.05
    ror
    0.05
    ä½ķå¿ħ
    0.05
    æķĻ主
    0.05
    æķĻå¾Ĵ
    0.05
     modeling
    0.05
    éģĵä¸Ĭ
    0.05
    ogn
    0.05
     Cogn
    0.05
    Activations Density 0.024%

    No Known Activations