© 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. 36801
    Prev
    Next
    INDEX
    Explanations

    history/Guinness records

    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
     Bless
    -0.09
    åľ°å¤Ħ
    -0.09
    åĵij
    -0.09
    éĹ¹
    -0.08
    raud
    -0.08
    æĦ«
    -0.08
    åħ¨å¥Ĺ
    -0.08
     Reflex
    -0.08
    åıįåºĶ
    -0.08
    ç´ł
    -0.08
    POSITIVE LOGITS
    åİĨåı²
    0.18
     history
    0.17
    åİĨåı²ä¸Ĭ
    0.16
     History
    0.14
    åİĨåı²æĢ§
    0.14
    çļĦåİĨåı²
    0.14
    history
    0.14
    åı²
    0.14
    æŃ·åı²
    0.14
     иÑģÑĤоÑĢии
    0.14
    Activations Density 0.058%

    No Known Activations