© 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. 35868
    Prev
    Next
    INDEX
    Explanations

    organizational hierarchy and reporting structure

    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
    ä¸ŃåĽ½æ±½è½¦
    -0.10
    кла
    -0.09
    å»Ľ
    -0.09
    æķĪçĽĬ
    -0.09
    é©Ń
    -0.09
    æ¬ł
    -0.09
    åĪ®
    -0.09
    æľīæľŁ
    -0.09
    -tool
    -0.09
    çĻ»åľº
    -0.09
    POSITIVE LOGITS
     structure
    0.15
    ç»ĵæŀĦ
    0.14
    å±Ĥ级
    0.13
    _structure
    0.13
    æŀ¶æŀĦ
    0.13
    structure
    0.13
    .structure
    0.12
     Structure
    0.11
    Structure
    0.11
     hierarchy
    0.11
    Activations Density 0.098%

    No Known Activations