© 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. 54468
    Prev
    Next
    INDEX
    Explanations

    got this from

    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
    çģ«çĤ¬
    -0.09
    çĻĸ
    -0.09
    ắn
    -0.09
    æĹħ游度åģĩ
    -0.09
    UCT
    -0.09
    nyder
    -0.08
    ä¹ı
    -0.08
    VERS
    -0.08
    ussia
    -0.08
    大åŀĭ
    -0.08
    POSITIVE LOGITS
    æĬļ
    0.10
    ĥģ
    0.09
    çĥ¨
    0.08
    zee
    0.08
    说æľį
    0.08
    å¥ĸ
    0.08
     Gos
    0.08
    æĦıè§ģåıįé¦Ī
    0.08
    庶
    0.08
    åIJĪä½ľåįıè®®
    0.08
    Activations Density 0.153%

    No Known Activations