© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31403
    Prev
    Next
    INDEX
    Explanations

    summon, conj, conjunction

    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
    wards
    -0.09
    è½±
    -0.09
    çĺł
    -0.08
    urement
    -0.08
    å¹´é¾Ħ
    -0.08
    agram
    -0.08
    ç§ijæĬĢåĽŃ
    -0.08
    æĬī
    -0.08
    æŃĩ
    -0.08
    ening
    -0.08
    POSITIVE LOGITS
     forth
    0.10
    oused
    0.10
    ously
    0.10
    ling
    0.10
    eer
    0.09
    innen
    0.09
    Ñĩи
    0.09
    rok
    0.09
    棣
    0.09
    äºĨä¸Ģ声
    0.09
    Activations Density 0.019%

    No Known Activations