© 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. 58904
    Prev
    Next
    INDEX
    Explanations

    verbs of motion

    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
    ast
    -0.09
    èĵij
    -0.09
    对æĪij
    -0.09
    æĺĶ
    -0.09
    çīĽ
    -0.08
    åľ¨è¿ĻéĩĮ
    -0.08
    çĪ±ç¾İ
    -0.08
    楼
    -0.08
     Newton
    -0.08
    æĶ¶åĽŀ
    -0.08
    POSITIVE LOGITS
    çĥı
    0.10
    带ä¸Ĭ
    0.10
    åİ»åģļ
    0.10
    主æĮģ
    0.09
    è¾Ł
    0.09
    严
    0.09
    uned
    0.09
    客æ°Ķ
    0.09
    akest
    0.09
     èĭ¥è¦ģ
    0.09
    Activations Density 0.045%

    No Known Activations