© 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. 9373
    Prev
    Next
    INDEX
    Explanations

    tool or instrument

    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
    /projects
    -0.09
    ä¸į容
    -0.09
    OOT
    -0.09
    rü
    -0.09
     rek
    -0.09
    çĭ¬èĩª
    -0.09
    éĨĴ
    -0.08
    åºŁ
    -0.08
    大åħ¨
    -0.08
    è´ª
    -0.08
    POSITIVE LOGITS
    å·¥åħ·
    0.29
     tool
    0.25
     tools
    0.25
    åĪ©åĻ¨
    0.22
     herramient
    0.20
    æīĭ段
    0.20
    æѦåĻ¨
    0.19
     Tool
    0.18
    tools
    0.18
     Tools
    0.17
    Activations Density 0.130%

    No Known Activations