© 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. 20420
    Prev
    Next
    INDEX
    Explanations

    hypertension management

    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
    æĨ©
    -0.08
    meni
    -0.07
    templ
    -0.07
    ána
    -0.07
    çĶ±ä¼ģä¸ļ
    -0.07
    बà¤Ĥध
    -0.07
    optimizer
    -0.06
    à¸ĵะ
    -0.06
    类产åĵģ
    -0.06
    elih
    -0.06
    POSITIVE LOGITS
    0.06
    头çĹĽ
    0.05
    ge
    0.05
    Cele
    0.05
     simply
    0.05
    é«ĺè¡Ģåİĭ
    0.05
    ve
    0.05
    è¿ijè§Ĩ
    0.05
     Ch
    0.05
    ç®Ģåįķ
    0.05
    Activations Density 0.021%

    No Known Activations