© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51834
    Prev
    Next
    INDEX
    Explanations

    invitation and invitations

    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
    owie
    -0.12
    åŃ¦å®¶
    -0.10
    çī¯
    -0.09
    -0.09
    unsch
    -0.09
    ëģ¼
    -0.09
    bol
    -0.08
    kok
    -0.08
    à¹Ģà¸Ńา
    -0.08
     Cliff
    -0.08
    POSITIVE LOGITS
    å¨ħ
    0.10
    رع
    0.09
    egan
    0.08
    éĻµ
    0.08
     tar
    0.08
    æĮĤçĿĢ
    0.08
    apg
    0.08
    åĩºçİ°äºĨ
    0.08
    éĢ¡
    0.08
    agar
    0.08
    Activations Density 0.007%

    No Known Activations