© 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. 57381
    Prev
    Next
    INDEX
    Explanations

    inhibitory

    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
    åī¥å¤º
    -0.11
    labs
    -0.10
    æ¤į
    -0.09
    å¾ģéĽĨ
    -0.09
    æł¸åĩĨ
    -0.09
    å®ıä¼Ł
    -0.09
     Estr
    -0.09
    _itr
    -0.09
    èµĦæºIJåħ±äº«
    -0.09
    åĽŀæĶ¶
    -0.08
    POSITIVE LOGITS
    æĬĹæĭĴ
    0.13
    éħįåIJĪ
    0.11
    æĬµæĬĹ
    0.11
    åıįæĬĹ
    0.11
    顽强
    0.10
    积æŀģéħįåIJĪ
    0.10
    éĢĥè·ij
    0.10
    åĿļ
    0.10
     resilient
    0.09
     resistant
    0.09
    Activations Density 0.235%

    No Known Activations