© 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. 18685
    Prev
    Next
    INDEX
    Explanations

    but introducing contrast

    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
    æ±Ĥæĺ¯
    -0.07
    amac
    -0.07
     &_
    -0.06
    usif
    -0.06
    å®ĥåħ·æľī
    -0.06
    -Star
    -0.06
     GÅĤów
    -0.06
    å®ĥæĺ¯ä¸Ģç§į
    -0.06
    çĪ¬èµ·æĿ¥
    -0.06
    æĸĩçIJĨ
    -0.06
    POSITIVE LOGITS
    ens
    0.06
    æĭĽ
    0.05
    ize
    0.05
    ied
    0.05
    主é¢ĺæķĻèĤ²
    0.05
    ä½ıå¤Ħ
    0.05
     herself
    0.05
    æľī
    0.05
    ä
    0.05
    èĸĦ
    0.05
    Activations Density 0.031%

    No Known Activations