© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36942
    Prev
    Next
    INDEX
    Explanations

    ruled out or missed

    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
    åºķæ°Ķ
    -0.10
    éĢĤåIJĪèĩªå·±
    -0.09
    ä¸Ģåı£
    -0.09
    æģ°
    -0.09
     sank
    -0.09
    平稳
    -0.08
    åįij
    -0.08
    éĺ¿æ£®
    -0.08
    ç¾İè§Ĥ
    -0.08
    åĵij
    -0.08
    POSITIVE LOGITS
    缺
    0.08
    缺å¸Ń
    0.08
    edin
    0.08
     CONDITION
    0.08
    acha
    0.08
    èĩ³å°ij
    0.08
    META
    0.08
    ç»Ĩå¾®
    0.08
    oot
    0.08
    é¹Ħ
    0.08
    Activations Density 0.034%

    No Known Activations