© 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. 5639
    Prev
    Next
    INDEX
    Explanations

    comment sections

    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
    ORIA
    -0.10
    Touches
    -0.09
     Rankings
    -0.08
    ToFit
    -0.08
    enticator
    -0.08
    çİ
    -0.08
    饴
    -0.08
    輩
    -0.08
    éĥ½åĸľæ¬¢
    -0.08
    oria
    -0.08
    POSITIVE LOGITS
    æī©æķ£
    0.10
    åīįçŀ»
    0.10
    çķĶ
    0.09
     cis
    0.09
    大家ä¸Ģèµ·
    0.09
    éĽ¢ãĤĮ
    0.09
    ICI
    0.09
    ãĤ³ãĥ¼ãĥ
    0.09
    é¢Ħæ¡Ī
    0.08
    ici
    0.08
    Activations Density 0.037%

    No Known Activations