© 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. 6981
    Prev
    Next
    INDEX
    Explanations

    LP, GP, HP (limited partners, games played, high pressure)

    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
    åĴİ
    -0.11
    æĥ®
    -0.10
    å¤ļ家
    -0.09
    osphere
    -0.08
    å¤ļæĸ¹
    -0.08
    羣æĥħ
    -0.08
    éĹ¹
    -0.08
    onomic
    -0.08
    alan
    -0.08
    _FM
    -0.08
    POSITIVE LOGITS
    iture
    0.10
    greg
    0.09
    AREN
    0.09
    ä»İæѤ
    0.09
     unre
    0.09
    åľ¨äº¬
    0.08
    SOR
    0.08
    aje
    0.08
    nel
    0.08
    zed
    0.08
    Activations Density 0.060%

    No Known Activations