© 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. 55989
    Prev
    Next
    INDEX
    Explanations

    choose from options

    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
    æĤĦçĦ¶
    -0.08
    æĬĬè¿Ļ个
    -0.08
    Alg
    -0.08
    å¸ģ
    -0.08
    wald
    -0.08
    oux
    -0.08
    çļĦçIJĨæĥ³
    -0.08
    ç©Ĺ
    -0.08
    æĢ»åħ¬åı¸
    -0.08
    éļıåį³
    -0.08
    POSITIVE LOGITS
    etadata
    0.10
    èĥľä»»
    0.09
    èijŃ
    0.09
    hoc
    0.09
    ème
    0.08
    asts
    0.08
    建åįİ
    0.08
    åĩ«
    0.08
    overrides
    0.08
    åªļ
    0.08
    Activations Density 0.005%

    No Known Activations