© 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. 51936
    Prev
    Next
    INDEX
    Explanations

    towers and structures

    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
    phen
    -0.09
    æĢı
    -0.09
    åĭĥåĭĥ
    -0.09
    èī°è¾Ľ
    -0.09
    orny
    -0.09
    ä¸Ģçīĩ
    -0.09
     Tome
    -0.08
    ä¸Ģåľº
    -0.08
    âĹĦ
    -0.08
    çĽ¸ä¿¡
    -0.08
    POSITIVE LOGITS
    å¡Ķ
    0.12
     towers
    0.12
     tower
    0.12
     Towers
    0.11
    tower
    0.11
     crane
    0.09
    RIPT
    0.09
    å±¹
    0.09
    èĢ¸
    0.08
    culated
    0.08
    Activations Density 0.025%

    No Known Activations