© 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. 52890
    Prev
    Next
    INDEX
    Explanations

    .io, .in, .com

    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
    æĭĬ
    -0.10
    çĻ¾å®¶
    -0.10
    umo
    -0.10
    .frequency
    -0.09
     Bowman
    -0.09
    åłĥ
    -0.09
    енÑĤа
    -0.09
    ilog
    -0.09
    ä¸į失
    -0.09
    zeug
    -0.09
    POSITIVE LOGITS
    iani
    0.10
    ä¸įäºĨ
    0.09
    å¸ĪåħĦ
    0.08
    ç»ĻäºĨæĪij
    0.08
    latin
    0.08
    æĥ¹
    0.08
    åijĬè¯īæĪij
    0.08
    çĶ»çĶ»
    0.08
    _ADV
    0.08
    Indented
    0.08
    Activations Density 0.015%

    No Known Activations