© 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. 20362
    Prev
    Next
    INDEX
    Explanations

    vermont, vermiculin, vermeersch

    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
    æĪij们ä¸Ģèµ·
    -0.11
    å®ĵ
    -0.09
    ç«łç¨ĭ
    -0.09
    å®ŀåľ¨
    -0.09
    ä¸ŃåİŁ
    -0.09
    æģ
    -0.09
     Charl
    -0.09
    ][/
    -0.08
    ride
    -0.08
    å½Ģ
    -0.08
    POSITIVE LOGITS
    主ä¸ļ
    0.09
    æĶ»
    0.09
    ç¿Ģ
    0.09
    äºĪ
    0.08
    gne
    0.08
    ennis
    0.08
    ниÑĨа
    0.08
    ìķħ
    0.08
    çģ¶
    0.08
    phis
    0.08
    Activations Density 0.002%

    No Known Activations