© 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. 27798
    Prev
    Next
    INDEX
    Explanations

    spines of fins

    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
    ç¥ļ
    -0.09
    ä½£
    -0.09
    使åĬ²
    -0.09
    ä¸ĢæŶ
    -0.09
    åĩĨç¡®
    -0.09
    缸继
    -0.09
    kü
    -0.08
    è¾±
    -0.08
     sarc
    -0.08
    æīĭæĮģ
    -0.08
    POSITIVE LOGITS
    å®ķ
    0.09
    çŁ¥
    0.09
    æµģåħ¥
    0.08
    èķ´
    0.08
    éĩįçĶŁ
    0.08
    æ¶Įçİ°
    0.08
    igan
    0.08
     temper
    0.08
    åģ¥èº«
    0.08
    åĨįéĢł
    0.08
    Activations Density 0.151%

    No Known Activations