© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36364
    Prev
    Next
    INDEX
    Explanations

    dam with suffix or name

    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
    ç²Ŀ
    -0.10
    erner
    -0.10
    شت
    -0.09
    侪
    -0.09
    atcher
    -0.09
    çĹĩ
    -0.09
    ãģĦãģĨ
    -0.09
    grund
    -0.08
    åĽłä¸ºä»ĸ
    -0.08
    imen
    -0.08
    POSITIVE LOGITS
    ļ
    0.10
    edList
    0.09
    issement
    0.09
    ascus
    0.09
    oose
    0.09
    ments
    0.09
    stoff
    0.09
    æŃ£å¸¸ä½¿çĶ¨
    0.09
    alysis
    0.09
    æ»ĵ
    0.08
    Activations Density 0.010%

    No Known Activations