© 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. 30452
    Prev
    Next
    INDEX
    Explanations

    choosing or selecting

    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
    RIES
    -0.08
    æĭĺ
    -0.08
    åĬłç´§
    -0.08
     Со
    -0.08
    OUR
    -0.08
    icity
    -0.08
    .SO
    -0.08
    >(()
    -0.08
    触åĬ¨
    -0.08
     Bundes
    -0.08
    POSITIVE LOGITS
    对æĸ¹
    0.09
    ãģ³
    0.09
    omi
    0.08
    å·´æĭī
    0.08
    彪
    0.08
    山寨
    0.08
    åĵģçīĮ形象
    0.08
    figure
    0.08
    angle
    0.08
    attrs
    0.08
    Activations Density 0.047%

    No Known Activations