© 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. 39868
    Prev
    Next
    INDEX
    Explanations

    Iran

    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
    人人
    -0.09
    é³
    -0.09
    å°ıç¼ĸ
    -0.08
     punt
    -0.08
    寡
    -0.08
     propTypes
    -0.08
     perm
    -0.08
    åħ¢
    -0.08
    out
    -0.08
    Mutable
    -0.08
    POSITIVE LOGITS
    èĶ·
    0.11
    åºĸ
    0.10
    éģIJ
    0.10
    åī½
    0.09
     Gain
    0.09
    andro
    0.09
    çķĻä½ı
    0.09
     cuts
    0.09
     Miche
    0.09
    .stem
    0.09
    Activations Density 0.319%

    No Known Activations