© 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. 51025
    Prev
    Next
    INDEX
    Explanations

    lamb, salmon, fish, beef, chicken

    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
    èijŃ
    -0.11
    è¿ĵ
    -0.10
    æijĬ
    -0.09
    水管
    -0.09
    gage
    -0.09
    èį¼
    -0.09
    erate
    -0.09
    liable
    -0.09
    æ©ĺ
    -0.09
    ä¸Ģåı¥
    -0.09
    POSITIVE LOGITS
    BorderColor
    0.09
    æķŀ
    0.08
    奥
    0.08
    Êī
    0.08
    åĪ©æ¶¦çİĩ
    0.08
    ળ
    0.08
    _skin
    0.08
     buz
    0.08
    CreateInfo
    0.08
    çIJĨè´¢
    0.08
    Activations Density 0.015%

    No Known Activations