© 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. 39026
    Prev
    Next
    INDEX
    Explanations

    mozilla, tabs, menu, tools, license

    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
    liers
    -0.11
    éŁŃ
    -0.10
    çĪ±ä½ł
    -0.10
    æľįåĬ¡äºİ
    -0.09
    åĬ¨æľº
    -0.09
    lier
    -0.09
    åľĪ
    -0.09
     Perc
    -0.08
    èĢ
    -0.08
    .idea
    -0.08
    POSITIVE LOGITS
    æīĺ
    0.09
    Abr
    0.09
    æ´¥
    0.09
     spo
    0.09
     moz
    0.08
    byn
    0.08
     Cant
    0.08
     Agu
    0.08
     Gol
    0.08
    å´¤
    0.08
    Activations Density 0.307%

    No Known Activations