© 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. 53363
    Prev
    Next
    INDEX
    Explanations

    acclaim, laud, praise

    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
    core
    -0.09
    åħĴ
    -0.09
    ä¸ī级
    -0.08
    ense
    -0.08
    _pes
    -0.08
    ä¸įå°ıçļĦ
    -0.08
    好转
    -0.08
    å¹²äºĭ
    -0.08
     Kens
    -0.08
    sav
    -0.08
    POSITIVE LOGITS
    ably
    0.11
    é¢Ĥ
    0.11
    ä¸įå·²
    0.11
    osti
    0.10
    çIJı
    0.10
    -worthy
    0.09
    ove
    0.09
    .Addr
    0.09
    æĸ¥
    0.09
    ä¹ĭä½ľ
    0.09
    Activations Density 0.027%

    No Known Activations