© 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. 18246
    Prev
    Next
    INDEX
    Explanations

    magazines

    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
    Separated
    -0.07
    åIJĥä¸į
    -0.06
    西éĥ¨
    -0.06
    ãĤħãģĨ
    -0.06
    人çĤº
    -0.06
    ebt
    -0.06
     giunta
    -0.06
     raped
    -0.06
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    -0.06
     pregh
    -0.06
    POSITIVE LOGITS
    S
    0.05
     exact
    0.05
    вин
    0.05
     sometimes
    0.05
    N
    0.05
     primi
    0.05
     conce
    0.05
    æķĪ
    0.05
     bottom
    0.05
     once
    0.05
    Activations Density 0.006%

    No Known Activations