© 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. 23156
    Prev
    Next
    INDEX
    Explanations

    requirements for annotation, US norm, summary box, pharmacy

    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
    è¿Ľè´§
    -0.11
    åįİå°Ķ
    -0.09
    åŁ·
    -0.09
    imer
    -0.09
    eton
    -0.09
    IGH
    -0.09
    quiries
    -0.09
    è°ļ
    -0.08
    åĨ³å¿ĥ
    -0.08
    simp
    -0.08
    POSITIVE LOGITS
    éĹ®åį·
    0.09
    鹧
    0.09
    å¤ĸåĮħ
    0.08
    èĥŃ
    0.08
     surv
    0.08
    çŃĶé¢ĺ
    0.08
    åıĤä¸İèĢħ
    0.08
     poll
    0.08
    collector
    0.08
     Bose
    0.08
    Activations Density 0.107%

    No Known Activations