© 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. 20273
    Prev
    Next
    INDEX
    Explanations

    can/may/might then verb

    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
    åħħ足çļĦ
    -0.06
    .lv
    -0.06
    çIJĥ迷们
    -0.06
    estal
    -0.06
    é«ĺ度
    -0.06
    inggu
    -0.06
     considerably
    -0.06
    imes
    -0.05
     доÑģÑĤ
    -0.05
    linger
    -0.05
    POSITIVE LOGITS
     Karma
    0.05
    _geom
    0.05
    åij¨è¾¹çݯå¢ĥ
    0.05
    meric
    0.05
    æ½ĩ
    0.05
    okin
    0.05
    0.05
    imen
    0.05
    amar
    0.05
     compl
    0.05
    Activations Density 0.001%

    No Known Activations