© 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. 61520
    Prev
    Next
    INDEX
    Explanations

    take a look

    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
    hatt
    -0.09
    ä¸įå°ij人
    -0.09
    è§ģåĪ°
    -0.08
    PMC
    -0.08
    обÑĢа
    -0.08
    çIJ¢
    -0.08
    Ø´ÙĤ
    -0.08
    æľ¬ç½ij
    -0.08
    çĻ»
    -0.08
    еÑħ
    -0.08
    POSITIVE LOGITS
    ters
    0.09
    åijĹ
    0.09
    åIJ¬åIJ¬
    0.09
    ÑĢай
    0.08
    æ¼Ĥ
    0.08
    éĻį温
    0.08
    è¾Ħ
    0.08
    LAY
    0.08
     Tube
    0.08
    管
    0.08
    Activations Density 0.016%

    No Known Activations