© 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. 9780
    Prev
    Next
    INDEX
    Explanations

    affected or involved

    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
    æ´µ
    -0.12
    å®ľ
    -0.09
    SSION
    -0.09
    åĨ³èĥľ
    -0.09
    ä¸įè¦ģåĨį
    -0.09
    åīįä¸Ģ天
    -0.09
    çŃīåİŁåĽł
    -0.09
    çļĦåĬªåĬĽ
    -0.09
    å·¥
    -0.09
     Gins
    -0.08
    POSITIVE LOGITS
    åıĹåĪ°å½±åĵį
    0.24
    åıĹå½±åĵį
    0.21
     affected
    0.15
    Affected
    0.14
    affected
    0.12
    å½±åĵį
    0.12
    åıĹçĽĬ
    0.12
    åıĹ害
    0.11
    åıĹåĪ°äºĨ
    0.11
     benefit
    0.10
    Activations Density 0.179%

    No Known Activations