© 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. 17564
    Prev
    Next
    INDEX
    Explanations

    indicator or marker

    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
    åĪĹ
    -0.09
     budget
    -0.09
    rij
    -0.09
    Budget
    -0.08
    æĺ¼å¤ľ
    -0.08
    ä¸ĥåħ«
    -0.08
     Ney
    -0.08
    æĢ»ä¹¦è®°åľ¨
    -0.08
    åĩłåįģ
    -0.08
    åįĥéĩĮ
    -0.08
    POSITIVE LOGITS
     Indicator
    0.16
    indicator
    0.16
     indicator
    0.15
     indicators
    0.15
    è¡¡éĩı
    0.14
    Indicator
    0.14
    æĮĩ示
    0.13
    æĮĩæłĩ
    0.12
    _indicator
    0.12
    çĽijæµĭ
    0.11
    Activations Density 0.189%

    No Known Activations