© 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. 11862
    Prev
    Next
    INDEX
    Explanations

    company names or technical terms

    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
    赶
    -0.09
    颦
    -0.09
    åĢ¦
    -0.08
    çľģæķĻèĤ²åİħ
    -0.08
    å«
    -0.08
     shy
    -0.08
    igs
    -0.08
     bis
    -0.07
    åıĶ
    -0.07
    离ä¸įå¼Ģ
    -0.07
    POSITIVE LOGITS
    propri
    0.10
    èĩªå®¶
    0.09
    .Experimental
    0.09
    ãģ°
    0.09
    muÅŁtur
    0.09
    éĺ
    0.09
    Ñģлов
    0.09
     division
    0.09
    ailand
    0.09
    äºĭä¸ļéĥ¨
    0.09
    Activations Density 0.665%

    No Known Activations