© 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. 36178
    Prev
    Next
    INDEX
    Explanations

    solid tumors

    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
     вÑĭполнен
    -0.10
    èĤ½
    -0.09
    è¹Ļ
    -0.09
    æ¹Ł
    -0.09
    çİ»çĴĥ
    -0.09
    LING
    -0.09
    ä¸Ģç»ı
    -0.09
    鼬
    -0.09
    bum
    -0.09
    交æ±ĩ
    -0.09
    POSITIVE LOGITS
     cancer
    0.18
    çĻĮ
    0.17
     Cancer
    0.16
    çĻĮçĹĩ
    0.16
     cancers
    0.14
    èĤºçĻĮ
    0.14
    èĩ´çĻĮ
    0.12
    æĬĹçĻĮ
    0.11
     metast
    0.10
    èĤ¿çĺ¤
    0.10
    Activations Density 0.648%

    No Known Activations