© 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. 63398
    Prev
    Next
    INDEX
    Explanations

    know that

    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
    IMIT
    -0.08
    åĬłéĩį
    -0.08
    è¦ģ注æĦı
    -0.08
    çIJ®
    -0.08
     Gar
    -0.08
    çģ«åĬĽ
    -0.08
    æ±Ľ
    -0.08
    çĶŁç´ł
    -0.08
    æĻºæħ§
    -0.08
    Gar
    -0.08
    POSITIVE LOGITS
    æ¸ħæ¥ļ
    0.10
    ä¸įæĺİçĻ½
    0.09
    æĢİä¹Īåģļ
    0.09
    身å¤Ħ
    0.09
     Bottle
    0.09
    æĻ°
    0.09
    宣
    0.09
    åĽ½æĥħ
    0.09
    å¦Ĥä½ķçľĭå¾ħ
    0.08
    å¦Ĥä½ķ
    0.08
    Activations Density 0.111%

    No Known Activations