© 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. 20148
    Prev
    Next
    INDEX
    Explanations

    Choi model

    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
    беÑĢна
    -0.06
    大å°ĨåĨĽ
    -0.06
    leen
    -0.06
    ultats
    -0.06
    ypse
    -0.05
    ekom
    -0.05
    mess
    -0.05
    gages
    -0.05
    emble
    -0.05
    oces
    -0.05
    POSITIVE LOGITS
     ‘
    0.05
    borough
    0.05
    endor
    0.05
    owitz
    0.05
    çŁ¥è¯ĨçĤ¹
    0.05
    svn
    0.05
    è¿ĺ好
    0.05
    S
    0.05
    icular
    0.05
    ISTA
    0.05
    Activations Density 0.111%

    No Known Activations