© 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. 51009
    Prev
    Next
    INDEX
    Explanations

    local shops and venues

    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
     singleton
    -0.10
    vac
    -0.10
    ä¸Ģç»Ħ
    -0.09
    íĭĢ
    -0.09
    主åħ¬
    -0.08
    à¹Ģà¸ķ
    -0.08
    SCAN
    -0.08
    singleton
    -0.08
    åIJİæİĴ
    -0.08
    度åģĩ
    -0.08
    POSITIVE LOGITS
    ä¹°åĪ°
    0.13
    åķĨåºĹ
    0.12
    å¸ĤåľºçļĦ
    0.11
    æĸ°åįİ
    0.11
    书åºĹ
    0.11
    è´Ńä¹°
    0.11
    å¸Ĥåľºä¸Ĭ
    0.10
     shops
    0.10
    åĶ®åįĸ
    0.10
     buying
    0.10
    Activations Density 0.095%

    No Known Activations