© 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. 9643
    Prev
    Next
    INDEX
    Explanations

    city and state/province names

    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
    iy
    -0.10
    lett
    -0.09
    ial
    -0.09
    boro
    -0.08
    quence
    -0.08
    robe
    -0.08
    çĥĪ
    -0.08
    peare
    -0.08
    italize
    -0.08
    uko
    -0.08
    POSITIVE LOGITS
    Ìģ
    0.10
    adero
    0.10
    ´
    0.10
    è£Ĩ
    0.10
    çĶŁç´ł
    0.10
    лÑıеÑĤ
    0.10
    æĥij
    0.10
    驹
    0.09
    ож
    0.09
    usch
    0.09
    Activations Density 0.059%

    No Known Activations