© 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. 33845
    Prev
    Next
    INDEX
    Explanations

    nursery and quarry

    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
     Hind
    -0.11
    éĻĪè¿°
    -0.10
     Plex
    -0.10
    æħµ
    -0.09
    OrDefault
    -0.09
    奢ä¾Ī
    -0.09
    åĦ¿
    -0.09
    çªĿ
    -0.09
    çĤ¹å¤ļ
    -0.08
     ÙĪاض
    -0.08
    POSITIVE LOGITS
    Ñħод
    0.09
    çĶ¨åĵģ
    0.09
    æĻħ
    0.08
    ogy
    0.08
    oice
    0.08
    祸
    0.08
    erer
    0.08
    åįĥæĸ¹
    0.08
    ists
    0.08
    itals
    0.08
    Activations Density 0.010%

    No Known Activations