© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20073
    Prev
    Next
    INDEX
    Explanations

    gearing up for

    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
    æıIJæĮ¯
    -0.09
    åĪ¶åº¦æĶ¹éĿ©
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    çĸ½
    -0.09
    社
    -0.09
    lat
    -0.09
     kè
    -0.08
    å¾Īå¤ļæŶåĢĻ
    -0.08
    大éŨ
    -0.08
    ovo
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģåľº
    0.10
     Bis
    0.09
    è¿İæİ¥
    0.09
    æĸ°ä¸Ģè½®
    0.09
     preparations
    0.09
    amins
    0.09
    åĩĨå¤ĩ
    0.09
    azes
    0.09
    åıĤåĬł
    0.08
    ä¸Ģåľº
    0.08
    Activations Density 0.016%

    No Known Activations