© 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. 63924
    Prev
    Next
    INDEX
    Explanations

    Robert followed by name parts

    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
    onne
    -0.12
    leep
    -0.10
    ر
    -0.10
    åŁĶ
    -0.09
    oust
    -0.09
    nda
    -0.09
    gmt
    -0.09
    ously
    -0.09
    æ±ķ
    -0.09
    avorite
    -0.09
    POSITIVE LOGITS
    aceous
    0.15
    sons
    0.12
    son
    0.11
    ãĤ¥
    0.10
    ening
    0.10
    inson
    0.10
    bery
    0.10
    ened
    0.09
    ness
    0.09
    alia
    0.09
    Activations Density 0.040%

    No Known Activations