© 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. 57349
    Prev
    Next
    INDEX
    Explanations

    dibs, dings, diphthongs

    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
    ivity
    -0.11
    sWith
    -0.11
    rez
    -0.10
    itan
    -0.09
    IFA
    -0.09
    rais
    -0.09
    aint
    -0.08
     lẽ
    -0.08
    anto
    -0.08
    FormsModule
    -0.08
    POSITIVE LOGITS
    飬
    0.12
    çĪµ
    0.11
    ег
    0.10
    产ä¸ļåıijå±ķ
    0.09
    家éŨåı£
    0.09
    umen
    0.09
    ç»ıèIJ¥èĮĥåĽ´
    0.09
    å´Ľ
    0.09
    橱
    0.09
    ãģĹãģı
    0.09
    Activations Density 0.012%

    No Known Activations