© 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. 51941
    Prev
    Next
    INDEX
    Explanations

    rule definitions or numbers

    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
    reb
    -0.11
    di
    -0.10
    èĥ½çľĭåĪ°
    -0.10
    ech
    -0.10
     giác
    -0.09
    dr
    -0.09
    ting
    -0.09
    ree
    -0.09
    TING
    -0.09
    eker
    -0.09
    POSITIVE LOGITS
    led
    0.11
    ivent
    0.10
    ledge
    0.10
    pec
    0.10
    vere
    0.09
    fulness
    0.09
    iola
    0.09
     dÄ±ÅŁÄ±
    0.09
    fully
    0.09
    tte
    0.09
    Activations Density 0.033%

    No Known Activations