© 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. 5336
    Prev
    Next
    INDEX
    Explanations

    visibility mediump pixels shaders normals

    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
    TED
    -0.09
    ctal
    -0.09
    ocks
    -0.09
    åĪijèѦ
    -0.09
    ç½ķ
    -0.09
    象
    -0.09
    åĪĹ
    -0.09
    罨
    -0.09
    _TS
    -0.08
    骥
    -0.08
    POSITIVE LOGITS
    主ä¹īæĢĿæĥ³
    0.11
    èĪªè¡Į
    0.10
    æĥľ
    0.10
    åĨ³èĥľ
    0.09
    çĽį
    0.09
    å¾Ĵ
    0.08
    ç»Ĩèħ»
    0.08
     اÙĦض
    0.08
    æį¡
    0.08
    éĹ®é¢ĺæĺ¯
    0.08
    Activations Density 0.233%

    No Known Activations