© 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. 27719
    Prev
    Next
    INDEX
    Explanations

    names like Hayes and Hayden

    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
    ning
    -0.09
    ย
    -0.08
    Ìģ
    -0.08
    ×ķת
    -0.08
    istic
    -0.08
    enor
    -0.08
    zier
    -0.08
    most
    -0.08
    åĢºæĿĥ
    -0.08
    lut
    -0.08
    POSITIVE LOGITS
    æѤåĪ»
    0.09
    ÑĤиÑĢ
    0.09
    åĩºä¼Ĺ
    0.08
    ãģĦãģ£ãģŁ
    0.08
    س
    0.08
    å®ļäºĨ
    0.08
    HDR
    0.08
    craft
    0.08
    ä¸įçĦ¶
    0.08
    ÑĤоп
    0.08
    Activations Density 0.006%

    No Known Activations