© 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. 9752
    Prev
    Next
    INDEX
    Explanations

    product names followed by descriptions

    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
    çįIJ
    -0.10
    atron
    -0.09
    Æ°ng
    -0.09
    åħ¬å¼Ģåıijè¡Į
    -0.09
    æĻĤãģ®
    -0.09
    ä½İ声
    -0.08
    URN
    -0.08
    æĪij没æľī
    -0.08
    æīī
    -0.08
    è¯ħ
    -0.08
    POSITIVE LOGITS
    probe
    0.10
     пÑĢоб
    0.09
    èijĨ
    0.08
     SO
    0.08
     Outcome
    0.08
    arters
    0.08
    quo
    0.08
    ä¸Ģä¸ĭ
    0.08
    å¼ĢåıijåĮº
    0.08
    èĢĺ
    0.08
    Activations Density 0.033%

    No Known Activations