© 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. 34031
    Prev
    Next
    INDEX
    Explanations

    gas debt, resume talks

    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
    çĽ²
    -0.11
    ä¸Ģç§Ĵ
    -0.10
    é²
    -0.09
     Everett
    -0.08
    æķ·
    -0.08
    æĻºæħ§
    -0.08
    arLayout
    -0.08
    æ¢ħèĬ±
    -0.08
     ÑĤоÑĢгов
    -0.08
    priv
    -0.08
    POSITIVE LOGITS
    è¿°
    0.11
    æŃ£å¥½
    0.10
    èݳ
    0.09
    å¿ĥèĦıçĹħ
    0.09
     Ryder
    0.09
    è´¿
    0.09
    ofilm
    0.09
     Disclaimer
    0.09
    iments
    0.09
    gons
    0.09
    Activations Density 0.028%

    No Known Activations