© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40390
    Prev
    Next
    INDEX
    Explanations

    room for or potential

    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
    Negative Logits
    èħĵ
    -0.10
    ogy
    -0.10
    综
    -0.10
    å°ijæķ°
    -0.09
    ubs
    -0.09
    ogl
    -0.09
    .inst
    -0.09
    åIJĸ
    -0.09
    çĽĹ
    -0.08
    é¦ĸéĥ½
    -0.08
    POSITIVE LOGITS
    åıijå±ķ空éĹ´
    0.17
    å¾Ī大çļĦ
    0.11
    空éĹ´
    0.11
     space
    0.11
    å¾Ĺåĩº
    0.10
     room
    0.10
    åľ°å¸¦
    0.10
    çļĦ空éĹ´
    0.10
     further
    0.09
    广éĺĶçļĦ
    0.09
    Activations Density 0.031%

    No Known Activations