© 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. 33440
    Prev
    Next
    INDEX
    Explanations

    motorsport terms

    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
    稿
    -0.10
    åĬ£
    -0.09
    æű
    -0.09
    åıĽ
    -0.08
    stry
    -0.08
     Canonical
    -0.08
    ÃŃc
    -0.08
     trek
    -0.08
    ittance
    -0.08
     Tactical
    -0.08
    POSITIVE LOGITS
    丰å¯Į
    0.10
    éĺ²çĽĹ
    0.09
    å®īéĺ²
    0.09
    éĩįçĤ¹é¢ĨåŁŁ
    0.09
    æĹłè¾ľ
    0.09
    æijĺ
    0.09
    åħį责声æĺİ
    0.09
    erus
    0.09
    plate
    0.08
     Daw
    0.08
    Activations Density 0.055%

    No Known Activations