© 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. 21849
    Prev
    Next
    INDEX
    Explanations

    lightning strikes

    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
    overe
    -0.10
    åĵĩ
    -0.09
     furnishings
    -0.08
    éĺµåľ°
    -0.08
    ular
    -0.08
    RLF
    -0.08
     Comparable
    -0.08
    人æ°ijæľįåĬ¡
    -0.08
    алÑĮнÑĭе
    -0.08
    utton
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.12
    storm
    0.11
    tru
    0.10
    è¾±
    0.10
    trap
    0.10
    èĪ¬
    0.09
    usual
    0.09
     ÑĤомÑĥ
    0.09
     usual
    0.09
     scl
    0.09
    Activations Density 0.006%

    No Known Activations