© 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. 37719
    Prev
    Next
    INDEX
    Explanations

    call for

    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
    ra
    -0.10
    åıĪæľī
    -0.08
     Bra
    -0.08
    åıĺçİ°
    -0.08
    rov
    -0.08
     lượng
    -0.08
    é³ĸ
    -0.08
     Ñģобой
    -0.08
    çĺŁ
    -0.08
    UNC
    -0.08
    POSITIVE LOGITS
    MLE
    0.10
    æľīæľŁ
    0.09
    飬
    0.09
    ×Ļת
    0.09
     Sợ
    0.08
    沪
    0.08
    æł¼å¤ĸ
    0.08
    SENT
    0.08
    elter
    0.08
    åī§éĻ¢
    0.08
    Activations Density 0.028%

    No Known Activations