© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51090
    Prev
    Next
    INDEX
    Explanations

    rolling stone, hills, grounds, mill, terrain

    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
    alus
    -0.10
    æĹłå¿§
    -0.09
    linger
    -0.09
    头éĥ¨
    -0.09
     lace
    -0.09
    éĺ¶
    -0.09
    ÑĤан
    -0.09
    nt
    -0.08
    pers
    -0.08
    ãģĭãĤĬ
    -0.08
    POSITIVE LOGITS
    etheless
    0.10
    æľīä¸įå°ij
    0.09
    enus
    0.09
    漪
    0.09
    aily
    0.09
    arily
    0.09
    ä¼Ļ
    0.09
    ocity
    0.09
    ãģ£ãģ¨
    0.09
    olds
    0.09
    Activations Density 0.005%

    No Known Activations