© 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. 54753
    Prev
    Next
    INDEX
    Explanations

    home business locations and activities

    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
     Lux
    -0.10
    让å®ĥ
    -0.10
     lux
    -0.10
    Lux
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    侨
    -0.09
    иÑĩно
    -0.09
    åĨĴ
    -0.09
     зÑĢ
    -0.09
    两次
    -0.09
    POSITIVE LOGITS
    åľ¨å®¶éĩĮ
    0.12
    åľ¨å®¶
    0.10
    åĬłå·¥
    0.09
    裾
    0.09
    ottage
    0.09
    oids
    0.09
    paginate
    0.08
    åĬŀåħ¬
    0.08
    åħ¼èģĮ
    0.08
    rena
    0.08
    Activations Density 0.062%

    No Known Activations