© 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. 32989
    Prev
    Next
    INDEX
    Explanations

    -er/-ger suffix

    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
    ìį¨
    -0.11
    æ¿ij
    -0.10
    ãĤ¡
    -0.10
    lish
    -0.10
    éģIJ
    -0.10
    ä¸įåĥı
    -0.10
    ãĤ©
    -0.09
    mie
    -0.09
    åŀ©
    -0.09
    ãģ¯ãģĺãĤģ
    -0.09
    POSITIVE LOGITS
    ingly
    0.08
    lijk
    0.08
    strom
    0.08
    æķ´é¡¿
    0.08
     Hath
    0.08
    onest
    0.08
    lijke
    0.08
    бав
    0.08
    ãģĦãģı
    0.08
    ments
    0.08
    Activations Density 0.016%

    No Known Activations