© 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. 20779
    Prev
    Next
    INDEX
    Explanations

    additional information, other tests, modify

    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
    wel
    -0.10
    atsu
    -0.09
    ATS
    -0.09
    大åħ¨
    -0.09
    .ShouldBe
    -0.08
    éĿŀ常å¤ļçļĦ
    -0.08
    æŁ´
    -0.08
    EVER
    -0.08
    çŃĭ
    -0.08
     uçu
    -0.08
    POSITIVE LOGITS
    å¦Ĥæŀľæľī
    0.19
    èĭ¥æľī
    0.19
    å¦Ĥæľī
    0.17
     nếu
    0.17
    å¿ħè¦ģçļĦ
    0.17
     еÑģли
    0.16
    IfNeeded
    0.15
     if
    0.15
    å¿ħè¦ģ
    0.15
    å¦Ĥæŀľ
    0.15
    Activations Density 0.149%

    No Known Activations