© 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. 50897
    Prev
    Next
    INDEX
    Explanations

    exclusive content and updates

    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
    å¥ı
    -0.09
    jon
    -0.08
     Panel
    -0.08
    åįĬå²Ľ
    -0.08
    ä¸İæŶ
    -0.08
    大æĸ¹
    -0.08
    ä¸Ĭæ¦ľ
    -0.08
    é«ĺæĸ°
    -0.08
    onta
    -0.07
    天æīį
    -0.07
    POSITIVE LOGITS
    Toe
    0.09
    ä½ĺ
    0.09
    éĢı
    0.09
    çī¹æ´¾
    0.09
    veis
    0.09
    tee
    0.09
    éģĺ
    0.08
    .dw
    0.08
    missive
    0.08
    éĩįä¸Ńä¹ĭéĩį
    0.08
    Activations Density 0.010%

    No Known Activations