© 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. 53860
    Prev
    Next
    INDEX
    Explanations

    actions completed

    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
    æľīä»»ä½ķ
    -0.10
    å±ĬæŶ
    -0.10
    inki
    -0.09
    ominator
    -0.09
    æīįèĥ½
    -0.08
    око
    -0.08
    åģ¾
    -0.08
     Wass
    -0.08
    UNT
    -0.08
    vido
    -0.08
    POSITIVE LOGITS
    æĪIJäºĨ
    0.14
    åĬłåħ¥äºĨ
    0.12
    æĪIJ为äºĨ
    0.12
    çľĭäºĨçľĭ
    0.11
    äºĨä¸Ģä¸ĭ
    0.11
     ÑģÑĤали
    0.11
    å¼Ģå§ĭäºĨ
    0.11
    åĪ¶å®ļäºĨ
    0.11
    åĽŀåĪ°äºĨ
    0.11
    éĢīæĭ©äºĨ
    0.11
    Activations Density 0.206%

    No Known Activations