© 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. 18165
    Prev
    Next
    INDEX
    Explanations

    finding abnormalities

    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
    UIT
    -0.07
    ropa
    -0.07
    éĹ»
    -0.05
    漫
    -0.05
     merce
    -0.05
    گر
    -0.05
    æĪĸå¤ļ个
    -0.05
    actic
    -0.05
    LEGRO
    -0.05
    æģ©
    -0.05
    POSITIVE LOGITS
    ulet
    0.06
     unfavor
    0.06
    ī
    0.06
    ph
    0.06
    ä»ĭäºİ
    0.05
    ulp
    0.05
    ullet
    0.05
     intentions
    0.05
     bounds
    0.05
    instead
    0.05
    Activations Density 0.067%

    No Known Activations