© 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. 9257
    Prev
    Next
    INDEX
    Explanations

    no more

    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
    åľ¨çİ°åľº
    -0.10
    ìķµ
    -0.09
    ottage
    -0.09
    å·²ç»ıæľīäºĨ
    -0.09
    argo
    -0.09
    .ua
    -0.09
    们éĥ½
    -0.09
    landers
    -0.09
    ä¸įåİ»
    -0.09
    ä¸Ģå¥Ĺ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.11
    缸äºĴ
    0.09
    ura
    0.09
    åįĩéĻį
    0.09
    theless
    0.08
    Vi
    0.08
     سÙĪÙī
    0.08
    æĻ®åıĬ
    0.08
    çĶŁçĶŁ
    0.08
    oyo
    0.08
    Activations Density 0.005%

    No Known Activations