© 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. 21039
    Prev
    Next
    INDEX
    Explanations

    black, gold, white, brown, blue colors

    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
    chiere
    -0.06
    plex
    -0.06
    å±ı
    -0.06
    åIJijåħļ
    -0.05
    âĢ¦
    -0.05
     ola
    -0.05
    ª
    -0.05
    å¯ĨåĪĩ
    -0.05
    ä¸Ĭè·¯
    -0.05
    å¿ĥ
    -0.05
    POSITIVE LOGITS
    ведÑĥ
    0.06
     diaria
    0.05
    umus
    0.05
    .JsonIgnore
    0.05
    eres
    0.05
    Franc
    0.05
    æŁ´
    0.05
    erno
    0.05
    asl
    0.05
    mw
    0.05
    Activations Density 0.026%

    No Known Activations