© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33902
    Prev
    Next
    INDEX
    Explanations

    HIV transmission and infection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ness
    -0.11
    lessly
    -0.10
    ams
    -0.10
    iveness
    -0.10
    most
    -0.09
    幺
    -0.09
    side
    -0.09
    ë¥ł
    -0.09
    atives
    -0.09
    Ľ
    -0.09
    POSITIVE LOGITS
    æ¤ħ
    0.12
    дж
    0.11
    ãĥ¼ãĤ·ãĥ§ãĥ³
    0.10
     Pathfinder
    0.09
    yla
    0.09
    ä¸įéĶĪ
    0.09
    inos
    0.09
     Buen
    0.09
    emonic
    0.08
    uary
    0.08
    Activations Density 0.309%

    No Known Activations