© 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. 31662
    Prev
    Next
    INDEX
    Explanations

    Niger, Nigel, Nigerian

    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
    èĻı
    -0.10
     Eag
    -0.10
    sch
    -0.09
     IPL
    -0.09
    san
    -0.09
    aping
    -0.08
     <![
    -0.08
    IPS
    -0.08
    åįģ足
    -0.08
    enstein
    -0.08
    POSITIVE LOGITS
    è§ŀ
    0.10
    顼
    0.09
    æľªæĽ¾
    0.09
    stamp
    0.08
    åIJİ代
    0.08
    леÑĩ
    0.08
    lio
    0.08
    åŁİå¸ĤçļĦ
    0.08
    erot
    0.08
    esti
    0.08
    Activations Density 0.005%

    No Known Activations