© 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. 8006
    Prev
    Next
    INDEX
    Explanations

    banished, precepts, versifier

    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
    åħ¨åĽ½äººæ°ij
    -0.09
    çĩĶ
    -0.09
     tieten
    -0.08
    å§Ĵ
    -0.08
    ogue
    -0.08
    ecture
    -0.08
    vertise
    -0.08
    ä¼ļè§ģ
    -0.08
    åĽ±
    -0.08
    æĶĢ
    -0.08
    POSITIVE LOGITS
    ç¦ıç¥ī
    0.08
     поиÑģк
    0.08
    odom
    0.08
     Nicol
    0.07
    æ·³
    0.07
     Naz
    0.07
    CAS
    0.07
    åıĬ以ä¸Ĭ
    0.07
     deep
    0.07
    ellipsis
    0.07
    Activations Density 0.123%

    No Known Activations