© 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. 19991
    Prev
    Next
    INDEX
    Explanations

    HIV transmission

    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
    ÑĥÑī
    -0.05
    obot
    -0.05
    é¦Ĩ
    -0.05
     Relief
    -0.05
    pl
    -0.05
     plurality
    -0.04
    enske
    -0.04
     recurring
    -0.04
     Sunshine
    -0.04
    åĽ¾åĴĮ
    -0.04
    POSITIVE LOGITS
     apos
    0.07
    кÑĢовен
    0.06
    sstr
    0.06
    umber
    0.06
    rav
    0.06
    éĩĩ访æĹ¶è¡¨ç¤º
    0.06
    ivec
    0.06
    latt
    0.06
    ฤ
    0.06
     Knot
    0.06
    Activations Density 0.039%

    No Known Activations