© 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. 1146
    Prev
    Next
    INDEX
    Explanations

    location or origin

    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
    æĽľ
    -0.11
    人人
    -0.10
    ourg
    -0.09
    导åħ¥
    -0.09
    odom
    -0.09
    ackbar
    -0.08
    æĸ°ä¸īæĿ¿
    -0.08
    rogen
    -0.08
    .tie
    -0.08
    æİı
    -0.08
    POSITIVE LOGITS
    身å¤Ħ
    0.16
    ä½įäºİ
    0.15
    located
    0.14
    è·Ŀ离
    0.14
     located
    0.13
    è·Ŀ
    0.12
    å¼Ĥåľ°
    0.12
     наÑħодиÑĤÑģÑı
    0.11
    éģ¥è¿ľ
    0.11
    è¿ľç¦»
    0.11
    Activations Density 0.114%

    No Known Activations