© 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. 56426
    Prev
    Next
    INDEX
    Explanations

    names and specific 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
    åŃ¦å®¶
    -0.10
    è¾ķ
    -0.10
    äu
    -0.10
    å»ĵ
    -0.10
    unner
    -0.09
    подоб
    -0.09
    ç©¿è¡£
    -0.09
    AndView
    -0.09
    æĪijä»¬ä¹Ł
    -0.09
    èģĶç³»æĪij们
    -0.09
    POSITIVE LOGITS
    ouse
    0.08
    eg
    0.08
    eci
    0.08
    ead
    0.08
    omat
    0.07
    èݱ
    0.07
    rew
    0.07
     Nobel
    0.07
    ee
    0.07
    妥
    0.07
    Activations Density 0.001%

    No Known Activations