© 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. 19515
    Prev
    Next
    INDEX
    Explanations

    grabbed or tugged

    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
    湫
    -0.08
    æķ²
    -0.08
    åIJİæĤĶ
    -0.08
    åĶ¯
    -0.08
    æ¼Ķ
    -0.08
    追赶
    -0.08
    éħ£
    -0.07
    å®Ĺ
    -0.07
     pinpoint
    -0.07
    ordion
    -0.07
    POSITIVE LOGITS
    äºİæĺ¯æĪij
    0.09
    æĪijçĪ±ä½ł
    0.09
    æ¾
    0.09
    åľ°åĿĹ
    0.09
    åī¯åİ¿éķ¿
    0.09
    èĥ³èĨĬ
    0.09
    getModel
    0.09
    è¯ĵ
    0.09
    çŁ¿åĮº
    0.09
    DMI
    0.09
    Activations Density 0.012%

    No Known Activations