© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37419
    Prev
    Next
    INDEX
    Explanations

    describing actions or states

    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
     ÑĢанее
    -0.08
     Ard
    -0.08
    بØŃ
    -0.08
    chten
    -0.08
    ites
    -0.08
    建ç«ĭèµ·
    -0.08
    nces
    -0.08
    .nt
    -0.08
    ãĤ®ãĥ£
    -0.08
     Wanted
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģåľº
    0.17
    äºĨ个
    0.17
    äºĨäºĽ
    0.17
     was
    0.16
     бÑĭла
    0.15
    äºĨä¸Ģ个
    0.15
    äºĨä¸Ģ
    0.15
    ãģĹãģ¾ãģĹãģŁ
    0.14
     бÑĭл
    0.14
     бÑĭло
    0.14
    Activations Density 1.223%

    No Known Activations