© 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. 21574
    Prev
    Next
    INDEX
    Explanations

    assessment, deployment, various

    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
    rebs
    -0.07
    feder
    -0.06
     trai
    -0.06
    ynd
    -0.06
    queta
    -0.06
    ylim
    -0.06
    steen
    -0.06
     Feder
    -0.06
    好
    -0.06
     féd
    -0.06
    POSITIVE LOGITS
    em
    0.05
    ç´łæľī
    0.05
    为çĪ±
    0.05
    ore
    0.05
    å¼Ģ个
    0.05
    rog
    0.05
    翻身
    0.05
    çļĦåıijå±ķåİĨç¨ĭ
    0.05
    çļĦåıijå±ķ
    0.05
    at
    0.05
    Activations Density 0.148%

    No Known Activations