© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50211
    Prev
    Next
    INDEX
    Explanations

    wanted to change

    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
    ÑĤик
    -0.08
     Race
    -0.08
    otto
    -0.08
    表éĿ¢ä¸Ĭ
    -0.08
    å®ĿçŁ³
    -0.08
     далеко
    -0.08
    åIJĥ
    -0.08
    tron
    -0.08
     Beach
    -0.08
    åij¼åºĶ
    -0.08
    POSITIVE LOGITS
    缨
    0.12
    æľīæĽ´å¤ļçļĦ
    0.10
    çĹķ
    0.10
    çľĭä¸Ģçľĭ
    0.10
    横
    0.10
    çľĭä¸Ģä¸ĭ
    0.09
    å¹²èĦĨ
    0.09
    avers
    0.09
    为ä»Ģä¹Īä¸į
    0.09
    acre
    0.09
    Activations Density 0.050%

    No Known Activations