© 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. 33026
    Prev
    Next
    INDEX
    Explanations

    HIV prevention and spread

    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
    æĭį
    -0.10
    èĭĵ
    -0.09
     Blow
    -0.09
    ä¸Ģç»Ħ
    -0.09
     Carlson
    -0.08
    æŀĩ
    -0.08
    ä½ľé£İ建设
    -0.08
    BUM
    -0.08
    PEG
    -0.08
    BAR
    -0.08
    POSITIVE LOGITS
    Haz
    0.10
     deb
    0.10
    çĭ©
    0.09
     Haz
    0.09
    çĩ¥
    0.08
    åĢŁ
    0.08
    å°±æĥ³
    0.08
    羣åĪĩ
    0.08
    æĻ®æŁ¥
    0.08
    .final
    0.08
    Activations Density 0.135%

    No Known Activations