© 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. 60822
    Prev
    Next
    INDEX
    Explanations

    place or role

    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
    ahl
    -0.09
    dal
    -0.09
    ç½®æį¢
    -0.09
    å®ħ
    -0.09
    ä¸įæĸŃå¢ŀ强
    -0.08
     Gladiator
    -0.08
    忽çķ¥äºĨ
    -0.08
    æĶ¹æĪIJ
    -0.08
    第ä¸ī个
    -0.08
    oidal
    -0.08
    POSITIVE LOGITS
    role
    0.12
     role
    0.12
     niche
    0.12
    èĪĶ
    0.10
    ROLE
    0.10
    place
    0.10
     Role
    0.10
    è§Ĵèī²
    0.10
    Role
    0.10
    .role
    0.10
    Activations Density 0.046%

    No Known Activations