© 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. 21898
    Prev
    Next
    INDEX
    Explanations

    Python `__init__`

    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
    ç¾Ķ
    -0.08
    ä¹ī
    -0.06
    ances
    -0.06
    aksi
    -0.05
    åĻ¨
    -0.05
    çľŁäºº
    -0.05
    ERICAN
    -0.05
    æ´ĽæĿī磶
    -0.05
    igned
    -0.05
    igger
    -0.05
    POSITIVE LOGITS
    åĤĻ
    0.06
    ensa
    0.06
     ÙĪاب
    0.06
    ekk
    0.05
    èĥ½æºIJ
    0.05
    later
    0.05
    åĤ»äºĨ
    0.05
    ç³»ç»Łä¸İ
    0.05
    çĻ¾åĪĨçĤ¹
    0.05
    APS
    0.05
    Activations Density 0.001%

    No Known Activations