© 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. 21461
    Prev
    Next
    INDEX
    Explanations

    variable declaration involving temp

    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
    xn
    -0.07
    ãģ£ãģĵãģĨ
    -0.07
    ìħĺ
    -0.07
    anches
    -0.06
    Ñīо
    -0.06
    Must
    -0.06
    smith
    -0.06
    æıĥ
    -0.06
    uruh
    -0.06
    udas
    -0.06
    POSITIVE LOGITS
    ç»´
    0.06
     dimension
    0.06
     Land
    0.05
    ä¸īæĺ¯
    0.05
    ukan
    0.05
    ediator
    0.05
     multic
    0.05
     McCoy
    0.05
    ament
    0.05
    ä¼ļéķ¿
    0.05
    Activations Density 0.001%

    No Known Activations