© 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. 2597
    Prev
    Next
    INDEX
    Explanations

    oops or operational mistakes

    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
    ä¸Ģåī¯
    -0.11
    æµĵæµĵçļĦ
    -0.10
    å®Įæķ´çļĦ
    -0.10
    èĭ¦èĭ¦
    -0.10
    åĬ¾
    -0.09
    å§ĭ建
    -0.09
    è¹²
    -0.09
    æĢ«
    -0.09
    éĺİ
    -0.09
    ãģ¾ãģķ
    -0.09
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.09
    itude
    0.09
    Occurred
    0.09
    iness
    0.09
    ilver
    0.09
    amac
    0.08
    ama
    0.08
     каж
    0.08
    ë§IJ
    0.08
    ery
    0.08
    Activations Density 0.002%

    No Known Activations