© 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. 6261
    Prev
    Next
    INDEX
    Explanations

    gardener or gardenia

    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
    ion
    -0.10
    ality
    -0.10
    otron
    -0.10
    tern
    -0.09
    累累
    -0.09
    chein
    -0.09
    ant
    -0.09
    air
    -0.09
    odor
    -0.09
    éĽī
    -0.09
    POSITIVE LOGITS
    oons
    0.10
    noon
    0.09
    rove
    0.09
    æĥľ
    0.08
    oined
    0.08
    cer
    0.08
    çĿ¬
    0.08
    hots
    0.08
    .vs
    0.08
    /***/
    0.08
    Activations Density 0.008%

    No Known Activations