© 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. 7544
    Prev
    Next
    INDEX
    Explanations

    before and after

    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
    LOPT
    -0.10
    obar
    -0.10
    麻
    -0.09
    vale
    -0.09
    .isSelected
    -0.09
    éĥĬ
    -0.09
    积æŀģæݢ索
    -0.09
    æį·
    -0.09
    ÂŃs
    -0.09
    ä½Ĩæĺ¯å¯¹äºİ
    -0.09
    POSITIVE LOGITS
    åīįåIJİ
    0.12
    (before
    0.11
    7
    0.11
    对æ¯Ķ
    0.11
    9
    0.11
    8
    0.11
    对çħ§
    0.10
    4
    0.10
    3
    0.10
     before
    0.10
    Activations Density 0.112%

    No Known Activations