© 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. 5865
    Prev
    Next
    INDEX
    Explanations

    severe

    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
    çĥŃæIJľ
    -0.10
    ühl
    -0.10
    ehler
    -0.09
    ÙĪع
    -0.08
    iec
    -0.08
    fone
    -0.08
    cip
    -0.08
     تعاÙĦÙī
    -0.08
    åĦ¿
    -0.08
    si
    -0.08
    POSITIVE LOGITS
    ities
    0.11
    æĥ³çŁ¥éģĵ
    0.10
    åī²
    0.10
    ityEngine
    0.10
    /ext
    0.10
    emente
    0.10
    åĴĶ
    0.10
    igne
    0.10
    è¿Ļæīįæĺ¯
    0.10
    itaire
    0.10
    Activations Density 0.024%

    No Known Activations