© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52615
    Prev
    Next
    INDEX
    Explanations

    end of phrases

    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
    å¼łåħĪçĶŁ
    -0.08
    çķĻå®Ī
    -0.08
     pij
    -0.08
    æĿİåħĪçĶŁ
    -0.08
    åįł
    -0.08
     Tooth
    -0.08
    éĵĥ
    -0.08
    ãģİ
    -0.08
     domic
    -0.08
    åĤ²
    -0.08
    POSITIVE LOGITS
    åħ®
    0.10
     unto
    0.10
    大æĪ·
    0.09
    åİĿ
    0.09
    强壮
    0.09
    微软
    0.09
    ä¹İ
    0.09
    å¯Ł
    0.09
    楽
    0.09
    ä¸ĥåįģ
    0.09
    Activations Density 0.178%

    No Known Activations