© 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. 28155
    Prev
    Next
    INDEX
    Explanations

    drug related activities and concepts

    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
     пÑĢоведен
    -0.10
    loh
    -0.10
     пÑĢовед
    -0.10
    _userdata
    -0.09
    obar
    -0.09
    igest
    -0.09
    PRESSION
    -0.09
    管çIJĨå±Ĥ
    -0.09
     Câm
    -0.09
     игÑĢов
    -0.09
    POSITIVE LOGITS
    ishly
    0.11
    ged
    0.10
    çķĮçļĦ
    0.09
    ivity
    0.09
    ster
    0.09
    è¡·
    0.09
    éŃģ
    0.09
    hound
    0.09
     comm
    0.08
    ging
    0.08
    Activations Density 0.025%

    No Known Activations