© 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. 35536
    Prev
    Next
    INDEX
    Explanations

    legal and governmental actions

    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
    æ¾İæ¹ĥæĸ°éĹ»
    -0.10
    å¾ģæľį
    -0.09
    Ñħод
    -0.09
    ä¸İæѤ
    -0.09
    éĤ£æł·çļĦ
    -0.09
     cones
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    æĭĽèĤ¡ä¹¦
    -0.08
    åij¼åĴĮ
    -0.08
    hos
    -0.08
    POSITIVE LOGITS
    åı¯çĶ¨
    0.09
    çļĦçĶ»éĿ¢
    0.09
    دار
    0.08
    ãĤªãĤ¹
    0.08
    ufs
    0.08
    åłŀ
    0.08
    _VF
    0.08
    åħ©äºº
    0.08
    IDADE
    0.08
    RAR
    0.08
    Activations Density 0.755%

    No Known Activations