© 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. 20143
    Prev
    Next
    INDEX
    Explanations

    arrow keys navigation

    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
    less
    -0.06
     thinly
    -0.06
    coach
    -0.06
    éros
    -0.05
    ÙĨÛĮ
    -0.05
    çek
    -0.05
    ached
    -0.05
    olas
    -0.05
     ben
    -0.05
    NullPointerException
    -0.05
    POSITIVE LOGITS
    ieger
    0.06
    _party
    0.06
    ypi
    0.05
    åĮ»èį¯
    0.05
    Ñıн
    0.05
    ansch
    0.05
    alink
    0.05
     Fitness
    0.05
    ä¸įä»ħæľī
    0.05
    èļģ
    0.05
    Activations Density 0.003%

    No Known Activations