© 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. 36363
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ton' or 'an'

    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
    hood
    -0.10
    æıĨ
    -0.09
    çĪ±åIJĥ
    -0.09
    åį¡å°Ķ
    -0.09
    ream
    -0.08
    çĿ£åĬŀ
    -0.08
    ä¸Ģä¸Ŀ
    -0.08
     comparatively
    -0.08
    æ´»
    -0.08
    年纪
    -0.08
    POSITIVE LOGITS
    çĿ«
    0.11
    nde
    0.09
    ока
    0.09
    èĩ»
    0.08
    å¿ĺ
    0.08
    acket
    0.08
    åħ´
    0.08
    anja
    0.08
     SEEK
    0.08
    Assembly
    0.08
    Activations Density 0.035%

    No Known Activations