© 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. 30142
    Prev
    Next
    INDEX
    Explanations

    arrest / arrested

    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
    ãĤ¤ãĥ«
    -0.10
    -même
    -0.09
    elves
    -0.09
    åįģ足
    -0.09
    ç¾İçļĦ
    -0.09
    -0.08
    dle
    -0.08
    amp
    -0.08
    alties
    -0.08
    æĹ©çĤ¹
    -0.08
    POSITIVE LOGITS
    ments
    0.11
    ees
    0.10
    ee
    0.09
    دة
    0.09
    æķĸ
    0.09
    æĪį
    0.08
    INAL
    0.08
    pes
    0.08
    [âĢ¦
    0.08
    ç³Ĭæ¶Ĥ
    0.08
    Activations Density 0.009%

    No Known Activations