© 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. 7360
    Prev
    Next
    INDEX
    Explanations

    about it

    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
    trail
    -0.10
    anyl
    -0.09
    zung
    -0.08
    åĪ«çļĦ
    -0.08
    anches
    -0.08
     Belgi
    -0.08
    ż
    -0.08
    icut
    -0.08
    imar
    -0.08
    izing
    -0.08
    POSITIVE LOGITS
     it
    0.17
    å®ĥ
    0.15
    å®ĥæĺ¯
    0.13
     ello
    0.12
    	it
    0.12
    æѤäºĭ
    0.11
    è¿Ļäºĭ
    0.11
    è¿Ļ件äºĭ
    0.10
    å®ĥåı¯ä»¥
    0.10
    ä¸Ģç¬Ķ
    0.10
    Activations Density 0.115%

    No Known Activations