© 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. 22977
    Prev
    Next
    INDEX
    Explanations

    health and lifestyle

    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
    èĮĦ
    -0.10
    æĺĨ
    -0.10
     наÑĢ
    -0.10
    lip
    -0.09
    ROP
    -0.09
    æĬ¢åħĪ
    -0.09
    å¸Ĥåľºä¸Ĭ
    -0.09
    åĮĸå¦Ĩ
    -0.09
    úb
    -0.09
    æī©å®¹
    -0.09
    POSITIVE LOGITS
    ä¸ĭåįĬ
    0.09
     dad
    0.08
    agra
    0.08
     desk
    0.08
    çĪ¸çĪ¸
    0.08
    appy
    0.08
    çĪ¸
    0.08
    ira
    0.08
    azer
    0.08
    zen
    0.08
    Activations Density 0.085%

    No Known Activations