© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7640
    Prev
    Next
    INDEX
    Explanations

    apiKey or auth credentials

    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
    pers
    -0.09
    æĮĩ导æĦıè§ģ
    -0.09
     Freund
    -0.08
    åºķå±Ĥ
    -0.08
    perc
    -0.08
    care
    -0.08
    æĭį
    -0.08
    inton
    -0.08
    lesh
    -0.08
    comb
    -0.08
    POSITIVE LOGITS
    åıĸå¾Ĺ
    0.10
    çĪŃ
    0.09
    å¤ĩæ¡Ī
    0.09
    éªĹåıĸ
    0.09
    çĥĪ
    0.09
    achts
    0.09
    çł£
    0.09
    bung
    0.09
    roach
    0.09
    åħ¬çĦ¶
    0.09
    Activations Density 0.255%

    No Known Activations