© 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. 21601
    Prev
    Next
    INDEX
    Explanations

    equations with variables like t, s, l

    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
    æĿ¡ä»¶æĺ¯
    -0.07
    venes
    -0.07
    æĢ§å·¥ä½ľ
    -0.06
    麻çĥ¦äºĨ
    -0.06
    å·®ãģĹ
    -0.06
    aup
    -0.06
     meilleur
    -0.06
    ailles
    -0.06
    nel
    -0.06
    byter
    -0.06
    POSITIVE LOGITS
    aze
    0.05
    oss
    0.05
    çĶ¨åĵģ
    0.05
    mong
    0.05
     close
    0.05
    inea
    0.05
    EXP
    0.05
    паниÑı
    0.05
    -ie
    0.05
    èį¼
    0.05
    Activations Density 0.093%

    No Known Activations