© 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. 17928
    Prev
    Next
    INDEX
    Explanations

    cellular telephone

    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
    ee
    -0.06
    ç´¯
    -0.06
    Ðĵо
    -0.05
    ow
    -0.05
     plains
    -0.05
    HT
    -0.05
    è¾ħåĬ©
    -0.05
    ube
    -0.05
     eet
    -0.05
     ÅĻe
    -0.05
    POSITIVE LOGITS
    ribly
    0.06
    kast
    0.06
    oui
    0.05
    ä¸Ĭæĸ°
    0.05
    riu
    0.05
    robi
    0.05
     himself
    0.05
    rai
    0.05
    宫éĩĮ
    0.05
    faith
    0.05
    Activations Density 0.322%

    No Known Activations