© 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. 20735
    Prev
    Next
    INDEX
    Explanations

    Doppler effect, red shift

    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
    ä¸ĩ个èµŀ
    -0.07
    jud
    -0.07
    [âĢ¦
    -0.07
    تاب
    -0.07
    گرÛĮ
    -0.06
    âĤ¬/
    -0.06
    ivit
    -0.06
    ведений
    -0.06
    ðŁĻĤ
    -0.06
    bove
    -0.06
    POSITIVE LOGITS
    encoding
    0.06
    åīįåIJİ
    0.06
     encoding
    0.05
    åı£
    0.05
     shortened
    0.05
     encode
    0.05
     Davidson
    0.05
     compression
    0.05
    è¿ľ
    0.05
    3
    0.05
    Activations Density 0.013%

    No Known Activations