© 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. 52560
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    æĿĸ
    -0.09
    æĻĴ
    -0.09
     Pence
    -0.08
    çļĦéĥ¨åĪĨ
    -0.08
    leaning
    -0.08
     erm
    -0.08
     Ritch
    -0.08
     Masc
    -0.08
    æijŀ
    -0.07
    APT
    -0.07
    POSITIVE LOGITS
    çĿģ
    0.11
    ahoo
    0.10
    éĻįä½İæĪIJæľ¬
    0.09
    åij¨åĪĬ
    0.09
    (Layout
    0.09
    é½IJ
    0.09
    åħĪåīį
    0.09
     hipp
    0.09
    å¹ķ
    0.09
    çľ¼åħī
    0.09
    Activations Density 0.037%

    No Known Activations