© 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. 2025
    Prev
    Next
    INDEX
    Explanations

    musicians' or artists' names

    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
    iras
    -0.10
    æ²»å®ī
    -0.10
    享
    -0.10
    обÑĢаз
    -0.10
    åħ¨å¤©
    -0.09
    åħ¥åľº
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    ä¸įèĥ½åĨį
    -0.09
    .GL
    -0.09
    UNE
    -0.09
    POSITIVE LOGITS
    ä¸Ŀ
    0.09
     slate
    0.08
    çIJ´
    0.08
    ornado
    0.08
    екÑĤ
    0.08
    5
    0.08
    .au
    0.08
    1
    0.07
    0
    0.07
    管
    0.07
    Activations Density 0.048%

    No Known Activations