© 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. 22471
    Prev
    Next
    INDEX
    Explanations

    [email opttmpl /ajax getti

    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
    èį¦
    -0.10
    å§ij
    -0.10
    毯
    -0.10
    çļĦæĪĺçķ¥
    -0.09
    å¿ĥèĦıçĹħ
    -0.09
    unas
    -0.09
    åĺ´å·´
    -0.09
     Toolbox
    -0.09
    åı£åij³
    -0.09
    ä¹³ä¸ļ
    -0.09
    POSITIVE LOGITS
    [email
    0.09
    [opt
    0.09
    çĪ±äºº
    0.08
    onom
    0.08
    VERS
    0.08
    tmpl
    0.08
    åľºæĻ¯
    0.08
    /ajax
    0.08
    getti
    0.07
    æĶ¶å½ķ
    0.07
    Activations Density 0.073%

    No Known Activations