© 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. 20953
    Prev
    Next
    INDEX
    Explanations

    can't believe

    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
    -wheel
    -0.09
    æĪijçĽ¸ä¿¡
    -0.09
    å¾Īéĩįè¦ģçļĦ
    -0.08
    inge
    -0.08
    æ¯Ķäºļ
    -0.08
    ä¹ĭ家
    -0.08
    çįIJ
    -0.08
    éĵµ
    -0.08
    åĵº
    -0.08
    lando
    -0.08
    POSITIVE LOGITS
    æīĭå¥Ĺ
    0.10
    ably
    0.10
    BAT
    0.09
     ÑģиÑĤÑĥаÑĨии
    0.09
     gloves
    0.09
    è¿İæĿ¥äºĨ
    0.09
    gage
    0.09
    çĦ¦
    0.08
    storm
    0.08
     glove
    0.08
    Activations Density 0.007%

    No Known Activations