© 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. 3355
    Prev
    Next
    INDEX
    Explanations

    cultural travel tourism

    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
    æ¼ł
    -0.09
    æķĪåĬĽ
    -0.09
    erte
    -0.09
     quán
    -0.09
    æĸ¹åľĨ
    -0.09
     íĻķ
    -0.08
    æħķ
    -0.08
    èŁ¾
    -0.08
    ophage
    -0.08
     concession
    -0.08
    POSITIVE LOGITS
    èĢĥå¯Ł
    0.10
    æĸĩåĮĸèĬĤ
    0.10
    æıŃ示
    0.10
    èĩªçĦ¶èĢĮ
    0.09
    访
    0.09
     Wh
    0.09
    åĺİ
    0.09
    è§ģåĪ°
    0.09
    建æĪIJ
    0.09
    Stamp
    0.09
    Activations Density 0.042%

    No Known Activations