© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34682
    Prev
    Next
    INDEX
    Explanations

    about + [it/this/them]

    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
    åı¦ä¸Ģä½į
    -0.10
    å¾Īå¤ļ
    -0.09
    afil
    -0.08
    渥
    -0.08
    yz
    -0.08
    etty
    -0.08
    nts
    -0.08
    1
    -0.08
    åĪ«çļĦ
    -0.08
    SD
    -0.08
    POSITIVE LOGITS
    å®ĥ
    0.31
    å®ĥ们
    0.26
     them
    0.24
    å®ĥåı¯ä»¥
    0.24
    å®ĥæĺ¯
    0.23
     ниÑħ
    0.20
     nó
    0.20
    å®ĥçļĦ
    0.19
     it
    0.19
    them
    0.19
    Activations Density 0.296%

    No Known Activations