© 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. 20264
    Prev
    Next
    INDEX
    Explanations

    academic major

    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
    à¸Ńà¸ļ
    -0.09
    ipp
    -0.09
    Diagram
    -0.09
     couch
    -0.08
     Cup
    -0.08
     Diagram
    -0.08
    åħĪçĶŁ
    -0.08
    ine
    -0.08
    .simps
    -0.08
    ÙĬØ©
    -0.08
    POSITIVE LOGITS
    åħ»æĪIJ
    0.09
    arms
    0.09
    ละà¸Ħร
    0.09
    elor
    0.08
    æľīä¿¡å¿ĥ
    0.08
    没éĶĻ
    0.08
    lib
    0.08
    çĽĨåľ°
    0.08
    erate
    0.08
    æ¯ķä¸ļçĶŁ
    0.08
    Activations Density 0.005%

    No Known Activations