© 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. 7332
    Prev
    Next
    INDEX
    Explanations

    magazines and publications

    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
    åºĨ幸
    -0.08
    atel
    -0.08
    ¹Ħ
    -0.08
    è¢Ń
    -0.08
    飾
    -0.08
    Nh
    -0.08
    çĥĪ
    -0.07
    £¼
    -0.07
    _PACK
    -0.07
     dise
    -0.07
    POSITIVE LOGITS
    rang
    0.11
     ATL
    0.10
    _NT
    0.10
    æĭĤ
    0.09
    iale
    0.09
    éĩįè¦ģåİŁåĽł
    0.09
    éĻ·åħ¥
    0.09
    侪
    0.09
    olvers
    0.09
    rieb
    0.09
    Activations Density 0.002%

    No Known Activations