© 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. 29971
    Prev
    Next
    INDEX
    Explanations

    collective activities/groups

    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
     expended
    -0.09
    å®ļçĤ¹
    -0.09
    ond
    -0.08
    åıĹçIJĨ
    -0.08
    ä¸Ńéĥ¨
    -0.08
    åij½
    -0.08
     Crush
    -0.08
     expend
    -0.08
    éĻª
    -0.08
    TERN
    -0.08
    POSITIVE LOGITS
    éĽĨä½ĵ
    0.11
    微信群
    0.11
    大家åĪĨ享
    0.11
    æ¿Ĵ临
    0.10
    åħ±åIJĮä½ĵ
    0.10
    å°ıåĮº
    0.09
     collective
    0.09
    åħ¬åħ±èµĦæºIJ
    0.09
    .BorderColor
    0.09
    çºł
    0.09
    Activations Density 0.053%

    No Known Activations