© 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. 3597
    Prev
    Next
    INDEX
    Explanations

    post messages or comment

    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
    éĶ²
    -0.10
    æĶ¾å¿ĥ
    -0.09
    åĸĦ
    -0.09
    欺è¯Ī
    -0.09
    oom
    -0.08
    aving
    -0.08
    _LSB
    -0.08
    ç¼®
    -0.08
    ä¸ŃåĽ½åĪ¶éĢł
    -0.08
    èļķ
    -0.08
    POSITIVE LOGITS
    TRACE
    0.09
    欣èµı
    0.09
    ppers
    0.08
    ,ep
    0.08
     admir
    0.08
    éĥĦ
    0.08
    车载
    0.08
     огÑĢани
    0.08
     TRACE
    0.08
     machinery
    0.08
    Activations Density 0.003%

    No Known Activations