© 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. 19137
    Prev
    Next
    INDEX
    Explanations

    suffix "-ity" or "-ation"

    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
    æĺ¯ä¸į
    -0.05
     deal
    -0.05
    pp
    -0.05
    .mod
    -0.05
     mistr
    -0.04
    omor
    -0.04
    iah
    -0.04
    Âł
    -0.04
    éģ
    -0.04
    à¸Ľà¸Ľ
    -0.04
    POSITIVE LOGITS
    alaria
    0.07
    该éĻ¢
    0.06
    æĸ°æ°Ķ象
    0.06
     gì
    0.06
    fection
    0.06
     nata
    0.06
    åľ¨ä¸ĬéĿ¢
    0.06
    ضاÙĬا
    0.06
    matter
    0.06
    -expand
    0.06
    Activations Density 0.036%

    No Known Activations