© 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. 30541
    Prev
    Next
    INDEX
    Explanations

    enc, ic, mac, ac suffixes

    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
    椽
    -0.09
    大å¹ħ度
    -0.09
    çªĴ
    -0.09
    ãģĤãĤĭ
    -0.09
    çĻ¾ä½Ļ
    -0.09
    iese
    -0.09
    è´§è¿IJ
    -0.08
    ç»Ĭ
    -0.08
    æĭĻ
    -0.08
    ÑĢам
    -0.08
    POSITIVE LOGITS
    å¼Ģåħĥ
    0.11
    lef
    0.10
    ero
    0.10
    åŃ£
    0.09
    entr
    0.09
    LEAR
    0.09
    缼ä¸ĸ
    0.09
    -metadata
    0.08
    lever
    0.08
    обоÑĢ
    0.08
    Activations Density 0.121%

    No Known Activations