© 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. 39816
    Prev
    Next
    INDEX
    Explanations

    Ray, Ray Charles, Raytheon

    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
    åŀĴ
    -0.10
    ä¸Ģå¤ľ
    -0.09
    çĥ
    -0.09
    å®ĵ
    -0.09
    éŃĦ
    -0.09
    bsd
    -0.09
    usher
    -0.09
    internet
    -0.09
    translations
    -0.09
    åĭĩæ°Ķ
    -0.08
    POSITIVE LOGITS
    nier
    0.09
    æľīæĿ¡ä»¶çļĦ
    0.08
    ickle
    0.08
    æľĢç¾İçļĦ
    0.08
    讨
    0.08
    ohl
    0.08
    èµĥ
    0.07
    AMS
    0.07
    ãģĬãĤĬ
    0.07
     Russell
    0.07
    Activations Density 0.022%

    No Known Activations