© 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. 11997
    Prev
    Next
    INDEX
    Explanations

    open to all

    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
    åºŀ
    -0.09
    个交æĺĵ
    -0.08
    æµħ
    -0.08
     игÑĢ
    -0.08
     surv
    -0.08
    平淡
    -0.08
    avig
    -0.08
    uries
    -0.08
    åIJĪ
    -0.08
    ä¼ļ导èĩ´
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.16
    æľīåħ´è¶£
    0.14
    ä»»ä½ķæŶåĢĻ
    0.13
    ä»»ä½ķ人éĥ½
    0.13
    åıªè¦ģ
    0.12
    åıªè¦ģæĺ¯
    0.12
     anybody
    0.12
     anyone
    0.12
    æľīä»»ä½ķ
    0.12
     Anyone
    0.12
    Activations Density 0.041%

    No Known Activations