© 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. 31622
    Prev
    Next
    INDEX
    Explanations

    this message or notice

    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
    åīįä¸Ģ天
    -0.10
    çªģçĦ¶
    -0.09
     recently
    -0.08
    è¿ijå¹´
    -0.08
    .WaitFor
    -0.08
    è¿ijæľŁ
    -0.08
    顶
    -0.08
    ALLE
    -0.08
    们éĥ½
    -0.08
     polys
    -0.08
    POSITIVE LOGITS
     ÑĢож
    0.10
    å°ıå¾®
    0.09
    lut
    0.09
     Cah
    0.09
    å¯Įè´µ
    0.09
    egin
    0.08
    æĬ¥ä»·
    0.08
    orial
    0.08
    çĽ´è¾¾
    0.08
    æ¹®
    0.08
    Activations Density 0.109%

    No Known Activations