© 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. 11842
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    åħ¶å®ĥ
    -0.12
     other
    -0.11
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    other
    -0.10
     autres
    -0.10
    åħ¶ä»ĸçļĦ
    -0.10
    åĪ«çļĦ
    -0.09
    .other
    -0.09
    åħ³æ³¨åº¦
    -0.08
     기íĥĢ
    -0.08
    POSITIVE LOGITS
    ä¹Łå¥½
    0.15
    ãĢįãĢĮ
    0.12
    ãģĹãģŁãĤĬ
    0.11
    ï¼īãĢģ
    0.10
     ë¬¼ë¡ł
    0.10
    æĢ§åĴĮ
    0.10
    ãģ¯ãĤĤãģ¡ãĤįãĤĵ
    0.10
    burger
    0.09
    èĥ½åĬĽåĴĮ
    0.09
    以åıĬ
    0.09
    Activations Density 0.697%

    No Known Activations