© 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. 16976
    Prev
    Next
    INDEX
    Explanations

    cream, lotions, watches, cameras, players

    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
    ugd
    -0.06
    为主
    -0.06
    ä½ľæ³ķ
    -0.06
    对çĻ½
    -0.06
    aeda
    -0.05
    rimon
    -0.05
     worked
    -0.05
    ément
    -0.05
    åį·
    -0.05
    kap
    -0.05
    POSITIVE LOGITS
    peria
    0.06
    æį·
    0.06
     souvenir
    0.06
    ross
    0.06
    pect
    0.05
    illard
    0.05
    åįĥ人
    0.05
    iah
    0.05
    гне
    0.05
    tere
    0.05
    Activations Density 0.001%

    No Known Activations