© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53372
    Prev
    Next
    INDEX
    Explanations

    poem or poems

    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
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.11
    nda
    -0.11
    anne
    -0.11
    ted
    -0.10
    ively
    -0.10
    omore
    -0.10
    ãģĦãģĨ
    -0.10
    umph
    -0.10
    apa
    -0.09
    sar
    -0.09
    POSITIVE LOGITS
    oland
    0.11
    eki
    0.10
    æĻ°
    0.10
    éĥ¢
    0.10
    matic
    0.09
    ãĤº
    0.09
    ichel
    0.09
    atically
    0.09
    icro
    0.08
    æĺ±
    0.08
    Activations Density 0.009%

    No Known Activations