© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48755
    Prev
    Next
    INDEX
    Explanations

    outdated or obsolete information

    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
    æIJĶ
    -0.10
    è´Ŀ
    -0.10
    æIJŀ好
    -0.09
    ä»ĸå¦Ī
    -0.09
    åħ¨æĹ¥
    -0.08
     Denied
    -0.08
    éĺħ读åħ¨æĸĩ
    -0.08
    çļĦæľºä¼ļ
    -0.08
    çIJĨæĢ§
    -0.08
    篦
    -0.08
    POSITIVE LOGITS
     outdated
    0.24
    èĢģæŧ
    0.23
    æŧ
    0.20
    åı¤èĢģ
    0.20
    åı¤ãģĦ
    0.19
     old
    0.19
    -old
    0.18
    èĪĬ
    0.18
    åı¤èĢģçļĦ
    0.17
    .old
    0.16
    Activations Density 0.266%

    No Known Activations