© 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. 31269
    Prev
    Next
    INDEX
    Explanations

    is/are followed by predicate nominative or adjective

    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
    åĿİ
    -0.09
    æł¼å±Ģ
    -0.09
    è¦Ĩ
    -0.09
    åĩ«
    -0.08
    EGA
    -0.08
    å¨ĺ家
    -0.08
    Dot
    -0.08
    /locale
    -0.08
    Validators
    -0.08
     Bite
    -0.08
    POSITIVE LOGITS
    ksz
    0.09
    olas
    0.08
     Kling
    0.08
    åIJŃ
    0.08
    æŃ¹
    0.08
    linger
    0.08
    4
    0.08
    ä¸Ģéĺµ
    0.08
    æĦıä¹ī
    0.08
    éĵł
    0.08
    Activations Density 0.054%

    No Known Activations