© 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. 17499
    Prev
    Next
    INDEX
    Explanations

    period or timeframe

    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
     Parts
    -0.06
     effective
    -0.06
    åħ«ä¹Ŀ
    -0.06
     Judgment
    -0.06
    è¹
    -0.05
    åħ³éĶ®çݯèĬĤ
    -0.05
     when
    -0.05
    ahal
    -0.05
    poz
    -0.05
    ife
    -0.05
    POSITIVE LOGITS
    á»ijc
    0.06
     Souza
    0.06
    è¿Ļæł·çļĦä¸Ģ个
    0.06
    ãģ£ãģį
    0.05
    éĢļ常为
    0.05
    à¹īวà¸Ļ
    0.05
     somebody
    0.05
    å¤ļ天
    0.05
    trad
    0.05
    äºīåħī
    0.05
    Activations Density 0.036%

    No Known Activations