© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7861
    Prev
    Next
    INDEX
    Explanations

    holds meaning | place | realise | micro

    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
    jsc
    -0.08
    çĶ³ãģĹ
    -0.08
    åĽ°
    -0.08
    éĩijå±±
    -0.08
     Sew
    -0.08
    两家
    -0.08
    ControlItem
    -0.08
    raits
    -0.08
    å¾Ĺåĩº
    -0.08
    shi
    -0.08
    POSITIVE LOGITS
    laces
    0.09
     maybe
    0.09
    åīįæīĢ
    0.09
    èµĦ产è¯Ħä¼°
    0.08
    æķ¦
    0.08
    èĪģ
    0.08
    æĹ¥èµ·
    0.08
    çĶļèĩ³æĺ¯
    0.08
    ä¹ŁåĽłæѤ
    0.08
    è¤Ĵ
    0.08
    Activations Density 0.091%

    No Known Activations