© 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. 18666
    Prev
    Next
    INDEX
    Explanations

    XML tags and attributes

    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
    ogia
    -0.06
    ä¸ļçļĦ
    -0.06
    oue
    -0.05
     helst
    -0.05
    sey
    -0.05
    öp
    -0.05
    jai
    -0.05
    alnız
    -0.05
    ayment
    -0.05
    ä¸ļ
    -0.05
    POSITIVE LOGITS
    wic
    0.06
    æ»ĭ
    0.06
    erule
    0.06
    raid
    0.06
    ingan
    0.06
     prévo
    0.05
    CID
    0.05
    icales
    0.05
    æ·±
    0.05
    acist
    0.05
    Activations Density 0.011%

    No Known Activations