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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20952
    Prev
    Next
    INDEX
    Explanations

    legal filings

    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
    ening
    -0.11
    ifier
    -0.10
    ingly
    -0.10
    loff
    -0.09
    大çĽĺ
    -0.09
    ãĥ³ãĤ°
    -0.09
    骧
    -0.09
    folk
    -0.09
     policym
    -0.09
    stype
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.10
    mates
    0.09
    arity
    0.09
    éĺĬ
    0.09
    GRES
    0.09
    éĥ½è¯´
    0.09
    axes
    0.09
     заÑıв
    0.08
    ØŃÙħ
    0.08
    unic
    0.08
    Activations Density 0.024%

    No Known Activations