© 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. 21502
    Prev
    Next
    INDEX
    Explanations

    Haddad, Hamza, Harem

    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
    æĿ°
    -0.09
    绵
    -0.08
     particulars
    -0.08
    èĪ¬çļĦ
    -0.08
    ç¶
    -0.08
     bred
    -0.08
     Heard
    -0.08
     ÑĢол
    -0.08
    åľ°éĿ¢
    -0.08
    è¯Ģ
    -0.08
    POSITIVE LOGITS
    utenberg
    0.10
    å§Ķå±Ī
    0.10
    å°ıäºĭ
    0.10
    sov
    0.09
    巴士
    0.09
    ä»Ģä¹Īäºĭæĥħ
    0.08
    _skb
    0.08
    à¸Ĺะ
    0.08
    åľį
    0.08
     STDERR
    0.08
    Activations Density 0.065%

    No Known Activations