© 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. 19248
    Prev
    Next
    INDEX
    Explanations

    ensuring security, quality, accuracy, safety

    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
    è¿ĩç¥ŀ
    -0.06
    inium
    -0.06
    legt
    -0.06
    atas
    -0.06
    iful
    -0.06
     milhão
    -0.06
    æ¸ħæ¸ħ
    -0.05
    Ø´
    -0.05
     ì²ł
    -0.05
    ìĥĺ
    -0.05
    POSITIVE LOGITS
    igen
    0.06
    æ®ĸ
    0.05
    åıĤä¸İè¯Ħ论
    0.05
    ophobic
    0.05
    اپ
    0.05
     isteyen
    0.05
    é«Ķ
    0.05
    Ñį
    0.05
    bine
    0.05
    иб
    0.05
    Activations Density 0.006%

    No Known Activations