© 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. 19198
    Prev
    Next
    INDEX
    Explanations

    elected officials and offices

    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
    æĸ°ä¸Ģè½®
    -0.09
    mania
    -0.09
    oute
    -0.08
    åıijå±ķéĺ¶æ®µ
    -0.08
    bru
    -0.08
    rail
    -0.08
    acre
    -0.08
    ÑĢеб
    -0.08
    ä¸ĬçıŃæĹı
    -0.08
    æŃ¦å£«
    -0.08
    POSITIVE LOGITS
    èĻı
    0.10
    ear
    0.10
    imers
    0.09
    ç½ijç«Ļåľ°åĽ¾
    0.09
    èļķ
    0.09
    éĶļ
    0.09
    æľºæŀĦ
    0.08
    ested
    0.08
    .DIS
    0.08
    eters
    0.08
    Activations Density 0.005%

    No Known Activations