© 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. 21497
    Prev
    Next
    INDEX
    Explanations

    knowledge and understanding

    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
    asher
    -0.05
    orca
    -0.05
    å¤Ń
    -0.05
    碩
    -0.05
     sani
    -0.05
    -dot
    -0.05
    æłijæŀĿ
    -0.05
     Epis
    -0.05
    æķ·è¡į
    -0.05
    indi
    -0.05
    POSITIVE LOGITS
    æĦŁåIJĮ
    0.07
    æĤ¯
    0.07
    åĪĩ身
    0.06
    æ·±åĪ»çIJĨ解
    0.06
     Nast
    0.06
    亲身ç»ıåİĨ
    0.06
    ç»ıåİĨè¿ĩ
    0.06
    缴éĿ¢
    0.06
    çݰ身
    0.06
    å¤ķ
    0.06
    Activations Density 0.110%

    No Known Activations