© 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. 10726
    Prev
    Next
    INDEX
    Explanations

    desert Rajasthan

    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
    ä»»æĢ§
    -0.10
    械
    -0.10
    éĩįéĩį
    -0.10
    รวà¸Ķ
    -0.09
    æľĪä¸Ń
    -0.09
    âĸ£
    -0.09
    åģ»
    -0.09
    olen
    -0.09
    enschaft
    -0.09
    åĻĮ
    -0.09
    POSITIVE LOGITS
    ogy
    0.10
    akit
    0.09
    aley
    0.09
    xon
    0.08
    _alive
    0.08
    oad
    0.08
    nce
    0.08
     Desert
    0.08
    çĶļèĩ³
    0.08
    å°¤åħ¶æĺ¯
    0.08
    Activations Density 0.020%

    No Known Activations