© 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. 30236
    Prev
    Next
    INDEX
    Explanations

    scored points

    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
    èĢĮçİ°åľ¨
    -0.10
    è¿Ļä¹Īå¤ļå¹´
    -0.10
    è¿Ļä¹Ī大
    -0.09
    è¿Ļä¹Ī
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
    éĢIJå¹´
    -0.09
    éķĤ
    -0.09
    ichert
    -0.09
    åIJĪæ³ķæĢ§
    -0.09
    èŀį为ä¸Ģä½ĵ
    -0.09
    POSITIVE LOGITS
    åĿĩ
    0.09
    åħ·å¤ĩ
    0.08
    åħ¶å®ĥ
    0.08
    _fore
    0.08
    amel
    0.08
     ÙĦدÙĬÙĩ
    0.08
    +-+-
    0.07
    åį«
    0.07
     giú
    0.07
    åģļåĪ°
    0.07
    Activations Density 0.012%

    No Known Activations