© 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. 16969
    Prev
    Next
    INDEX
    Explanations

    announcement, question, email

    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¡¡
    -0.06
    ingham
    -0.05
    odar
    -0.05
    erness
    -0.05
     first
    -0.05
    d
    -0.05
     primera
    -0.05
    ä»İä¸į
    -0.05
     pertama
    -0.05
    mans
    -0.05
    POSITIVE LOGITS
     cadr
    0.07
    Ú©ÙĨÙĪÙĨ
    0.07
    illo
    0.06
     ÙħجاÙĨ
    0.06
    æĤ¨åı¯èĥ½
    0.06
    agan
    0.06
    åħ¶è§ĤçĤ¹
    0.06
     remett
    0.06
     fordel
    0.06
    upro
    0.06
    Activations Density 0.001%

    No Known Activations