© 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. 20548
    Prev
    Next
    INDEX
    Explanations

    orders and purchases

    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
    åı£è¢ĭ
    -0.08
    ern
    -0.08
    Tre
    -0.08
    å¹³åĿ¦
    -0.08
    åħ«åŃĹ
    -0.08
    icker
    -0.08
    nob
    -0.08
    éķĽ
    -0.08
    礼åĵģ
    -0.08
    ä¸ĩåı°
    -0.07
    POSITIVE LOGITS
    åĪĿ次
    0.10
    è¿Ľä¸ĢæŃ¥
    0.09
    硼
    0.09
    ä½ķå¿ħ
    0.09
    _MISC
    0.09
    mvc
    0.09
    æĺĤ
    0.09
     FileAccess
    0.09
    é¦ĸ次
    0.09
    麻çĹ¹
    0.08
    Activations Density 0.026%

    No Known Activations