© 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. 9462
    Prev
    Next
    INDEX
    Explanations

    a + quantifier or descriptor

    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
    çĶ«
    -0.10
    ernet
    -0.09
    _nth
    -0.09
     clocks
    -0.08
    reh
    -0.08
    bane
    -0.08
    åĴİ
    -0.08
     ones
    -0.08
    å¹½
    -0.08
    çī¹æ®Ĭ
    -0.08
    POSITIVE LOGITS
    ãĤĤãģĦãģĦ
    0.09
    æŁľåı°
    0.09
    贵宾
    0.09
    åı¹æģ¯
    0.09
    æĪĺçķ¥æĢ§
    0.09
    éģĵ士
    0.09
     двоÑĢ
    0.08
    åĩŃ
    0.08
    è¿Ŀæ³ķè¿Ŀè§Ħ
    0.08
    èĤĭ
    0.08
    Activations Density 0.099%

    No Known Activations