© 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. 3929
    Prev
    Next
    INDEX
    Explanations

    tackling, hitting, and weight (pounds/lbs)

    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
    алÑĮн
    -0.09
    æµģ转
    -0.09
    ä¸ĭè¾¾
    -0.09
    åĺ´
    -0.08
    ä¿¡
    -0.08
     vap
    -0.08
     firing
    -0.08
    é¹Ī
    -0.08
    æIJģ
    -0.08
    çľº
    -0.08
    POSITIVE LOGITS
    æݥ触
    0.10
    èĩªç§°
    0.10
    æĮĩçĶ²
    0.10
    æı©
    0.09
    ä¸ĵçıŃ
    0.09
     tackle
    0.09
    çĤ¼
    0.09
    osite
    0.09
     конÑĤак
    0.09
     Nev
    0.09
    Activations Density 0.209%

    No Known Activations