© 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. 17611
    Prev
    Next
    INDEX
    Explanations

    adjectives describing services or properties

    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
     Nope
    -0.11
     ÑģобÑģÑĤвенно
    -0.09
    Çİ
    -0.09
    åĨĻçļĦ
    -0.09
    å´§
    -0.09
    éŃĶ鬼
    -0.09
    æīĢ说
    -0.09
    åħ¶ä»ĸ人
    -0.09
    arma
    -0.08
    ãģķãģ¦
    -0.08
    POSITIVE LOGITS
    åį´åıĪ
    0.10
    ãģĭãģ¤
    0.09
    èĢĮåıĪ
    0.09
     коÑĤоÑĢ
    0.08
     Bid
    0.08
    .bid
    0.08
    åıĪèĥ½
    0.08
    laden
    0.08
    åIJĮåŁİ
    0.08
     BRO
    0.08
    Activations Density 0.102%

    No Known Activations