© 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. 18982
    Prev
    Next
    INDEX
    Explanations

    `text` or `content` followed by HTML/attributes

    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
    çĦ¶å¤§
    -0.06
    éĺ²æļij
    -0.06
    ideo
    -0.06
    à¹Ģà¸Ħียà¸ĩ
    -0.06
    ÅĤat
    -0.06
    deos
    -0.06
    éļª
    -0.06
    פת
    -0.06
    ikiran
    -0.06
    ÑijÑĢ
    -0.06
    POSITIVE LOGITS
    ph
    0.05
    ÅĤÄĻ
    0.05
    aring
    0.05
    ×ķצ
    0.05
    oller
    0.05
    ue
    0.05
    ugada
    0.05
    ä½Ĩä¸įéĻIJäºİ
    0.05
    head
    0.05
    println
    0.05
    Activations Density 0.001%

    No Known Activations