© 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. 49172
    Prev
    Next
    INDEX
    Explanations

    after negative events

    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
     Zuk
    -0.09
     constantly
    -0.09
    涧
    -0.09
    èĭ¥å¹²
    -0.09
    oidal
    -0.09
    oha
    -0.08
    ç®Ģ约
    -0.08
    ä¾Ŀæŧæĺ¯
    -0.08
    常年
    -0.08
    ocha
    -0.08
    POSITIVE LOGITS
    便ä¼ļ
    0.11
    åī©
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    ảng
    0.09
    fin
    0.09
    ä»»ä½ķä¸Ģ个
    0.09
    íķĺê±°ëĤĺ
    0.09
    åİĺ
    0.09
    æij¹
    0.09
    åĵªä¸Ģ个
    0.09
    Activations Density 0.098%

    No Known Activations