© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19566
    Prev
    Next
    INDEX
    Explanations

    formulas and code symbols

    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
    наÑģÑĤоÑı
    -0.07
    ein
    -0.07
    eon
    -0.07
    er
    -0.06
    é¤
    -0.06
    een
    -0.06
    缸è¾ħ缸æĪIJ
    -0.06
    аем
    -0.06
    ease
    -0.06
    кÑĢо
    -0.06
    POSITIVE LOGITS
    ibble
    0.05
    jol
    0.05
    otal
    0.05
    è§Ĩè§īä¸Ĭ
    0.05
    ahl
    0.05
    nai
    0.04
    è¿ŀ
    0.04
     Customize
    0.04
    ä¸įçĦ¶
    0.04
    ί
    0.04
    Activations Density 0.021%

    No Known Activations