© 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. 27272
    Prev
    Next
    INDEX
    Explanations

    sport(s) car(s)

    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
    åĬŁå¾·
    -0.11
    温馨
    -0.09
    ä¼ļ议室
    -0.09
    çī¹æ´¾
    -0.08
    æļĸå¿ĥ
    -0.08
    èIJ¥åħ»ä»·åĢ¼
    -0.08
    椴
    -0.08
    ä¸Ģç¢Ĺ
    -0.08
    çĸ²æĥ«
    -0.08
     dou
    -0.08
    POSITIVE LOGITS
    éªij
    0.10
    对æĬĹ
    0.10
    ç»ķ
    0.10
     полÑĥÑĩен
    0.09
    社ä¼ļç»Ħç»ĩ
    0.09
    导åIJij
    0.09
    åħ¼é¡¾
    0.08
    èĭ
    0.08
    åĪĨè£Ĥ
    0.08
     compromise
    0.08
    Activations Density 0.026%

    No Known Activations