© 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. 17767
    Prev
    Next
    INDEX
    Explanations

    positive, negative, numbers

    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
    æŀī
    -0.07
    ikov
    -0.07
    å·¦åı³
    -0.06
    æĴ¼
    -0.06
    uffle
    -0.06
    å·¦åı³çļĦ
    -0.06
    ogo
    -0.06
    æIJħ
    -0.06
    änd
    -0.06
    æijĩæijĨ
    -0.05
    POSITIVE LOGITS
     positive
    0.08
    positive
    0.07
     Positive
    0.07
    _positive
    0.07
    Positive
    0.07
    为æŃ£
    0.06
     positivity
    0.06
     positif
    0.06
    æŃ£åIJij
    0.06
    æŃ£åĢ¼
    0.06
    Activations Density 0.080%

    No Known Activations