© 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. 16560
    Prev
    Next
    INDEX
    Explanations

    common word endings (.ed, .ated, .ased, .anned)

    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
    able
    -0.15
    ised
    -0.11
    istic
    -0.11
    ied
    -0.11
    ings
    -0.10
    äºĨèĩªå·±çļĦ
    -0.10
    iest
    -0.10
    /do
    -0.09
    er
    -0.09
    åĪ°æĿ¥
    -0.09
    POSITIVE LOGITS
    ness
    0.23
    evice
    0.16
    /generated
    0.14
    epend
    0.14
    efault
    0.14
    NESS
    0.14
    esign
    0.14
    etection
    0.13
    ialog
    0.13
    ä¸įèµ·
    0.13
    Activations Density 1.070%

    No Known Activations