© 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. 20470
    Prev
    Next
    INDEX
    Explanations

    contains, fork, tissues, PDF

    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
    lek
    -0.06
    ابÙĦØ©
    -0.06
    è¿Ľä¸ĢæŃ¥åıijå±ķ
    -0.06
    è¿Ľä¸ĢæŃ¥
    -0.06
    ÑįÑį
    -0.05
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    -0.05
    åĨħå¿ĥä¸ĸçķĮ
    -0.05
    ikte
    -0.05
    çĶ¸
    -0.05
    zie
    -0.05
    POSITIVE LOGITS
    bergen
    0.06
    lopen
    0.06
    ä¸į移
    0.06
    åħ¬åı¸æıIJä¾Ľ
    0.06
    µ
    0.06
    åĬĽçļĦ
    0.05
    HEET
    0.05
    çİĭä¹ĭ
    0.05
    å®ģ
    0.05
    è§ĴçļĦ
    0.05
    Activations Density 0.070%

    No Known Activations