© 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. 35089
    Prev
    Next
    INDEX
    Explanations

    bust or busted

    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
    er
    -0.10
    éħ®
    -0.09
    erer
    -0.09
    æīĭæİĮ
    -0.09
    erk
    -0.09
    å©¿
    -0.08
    ists
    -0.08
    ise
    -0.08
    çģ¼
    -0.08
    ENTS
    -0.08
    POSITIVE LOGITS
    itution
    0.11
    æİīäºĨ
    0.11
    folio
    0.10
    çĦ¶æĺ¯
    0.10
    rength
    0.09
    æİī
    0.09
    äºĨä¸Ģæī¹
    0.09
    iful
    0.09
    ties
    0.09
    -fw
    0.09
    Activations Density 0.005%

    No Known Activations