© 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. 37755
    Prev
    Next
    INDEX
    Explanations

    so far

    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
    ä¸įåľ¨ä¹İ
    -0.10
    ä¸īåĽĽ
    -0.10
    UGIN
    -0.09
    PropertyParams
    -0.09
    å¼ĢçĽĺ
    -0.09
    ESA
    -0.09
    ç»Ĵ
    -0.09
    åįģåĪĨéĴŁ
    -0.09
    è¾ĭ
    -0.08
    ì°¾
    -0.08
    POSITIVE LOGITS
    缮åīį为æŃ¢
    0.24
    è¿Ħä»Ĭ为æŃ¢
    0.18
    èĩ³ä»Ĭ
    0.16
    以æĿ¥
    0.15
    è¿Ħä»Ĭ
    0.15
    以ä¾Ĩ
    0.14
    æĪªèĩ³çĽ®åīį
    0.13
     bisher
    0.13
    å¹´æĿ¥
    0.12
    åĪ°çİ°åľ¨
    0.12
    Activations Density 0.051%

    No Known Activations