© 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. 18679
    Prev
    Next
    INDEX
    Explanations

    expression

    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
    abah
    -0.06
     ausger
    -0.06
    å±¥è¡ĮåIJĪåIJĮ
    -0.06
    人家
    -0.05
     entry
    -0.05
     Tune
    -0.05
    alina
    -0.05
    itel
    -0.05
    ober
    -0.05
    itra
    -0.05
    POSITIVE LOGITS
    è¯Ħä¼°
    0.07
    表达å¼ı
    0.06
     evaluation
    0.06
     evaluations
    0.06
    è´±
    0.06
    recursive
    0.05
    .evaluate
    0.05
     expression
    0.05
     ::=
    0.05
    级
    0.05
    Activations Density 0.061%

    No Known Activations