© 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. 8771
    Prev
    Next
    INDEX
    Explanations

    suspicion or suspect

    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
    CN
    -0.09
    atha
    -0.08
    éĩijå¥ĸ
    -0.08
    ä¸Ģå¤Ħ
    -0.08
    ç²ĺ
    -0.08
    è´¨
    -0.08
    oden
    -0.08
    unpack
    -0.08
     chiếu
    -0.08
    ipse
    -0.08
    POSITIVE LOGITS
    æĢĢçĸij
    0.19
     suspicions
    0.18
     suspicion
    0.18
     suspect
    0.15
     suspected
    0.14
    Sus
    0.13
    sus
    0.13
    çĸij
    0.13
    çĮľæµĭ
    0.13
     Sus
    0.12
    Activations Density 0.100%

    No Known Activations