© 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. 8682
    Prev
    Next
    INDEX
    Explanations

    freeze-dried

    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
    çijľ
    -0.10
    éĿŀåĩ¡
    -0.09
     Carroll
    -0.09
    spy
    -0.09
    ë¥ĺ
    -0.09
    SCP
    -0.09
    çı©
    -0.09
    воÑĢ
    -0.09
    屦
    -0.09
    igators
    -0.08
    POSITIVE LOGITS
     sink
    0.09
    èĮij
    0.09
    sink
    0.09
    tsky
    0.09
    æĭĸ
    0.09
    ä¸ĵä¸ļåĮĸ
    0.08
    çĥŁ
    0.08
    illard
    0.08
    ooks
    0.08
    íķĺ
    0.08
    Activations Density 0.005%

    No Known Activations