© 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. 36327
    Prev
    Next
    INDEX
    Explanations

    reported incidents

    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
    踪
    -0.10
    ç§ĺå¯Ĩ
    -0.09
    eper
    -0.09
    æļĹ
    -0.09
    kop
    -0.09
    CONN
    -0.09
    çľĭçĤ¹
    -0.09
    æļĹæļĹ
    -0.08
    quee
    -0.08
    æĸ©
    -0.08
    POSITIVE LOGITS
    å®īçĦ¶
    0.14
    å¹³å®ī
    0.12
    轻微
    0.11
    æįŁä¼¤
    0.11
    åıĹ伤
    0.11
    çļĦå®īåħ¨
    0.11
    幸好
    0.11
    å½ĵæŶçļĦ
    0.10
    çĸ¤çĹķ
    0.10
    åıĹæįŁ
    0.10
    Activations Density 0.061%

    No Known Activations