© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51608
    Prev
    Next
    INDEX
    Explanations

    may or could indicate possibility

    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
    åĨµ
    -0.09
    å®Ľ
    -0.08
    eses
    -0.08
    ç«Ļåľ¨
    -0.08
    PropertyChanged
    -0.08
    ven
    -0.08
    деж
    -0.08
     Mud
    -0.08
    许åı¯
    -0.08
    zia
    -0.08
    POSITIVE LOGITS
    åı¯èĥ½
    0.10
    åı¯èĥ½åŃĺåľ¨
    0.10
     возможно
    0.10
    éļıæŶ
    0.10
     possibly
    0.10
    haps
    0.10
    æľīæľĽ
    0.10
     fut
    0.10
    æľīåı¯èĥ½
    0.10
    æĬĽ
    0.10
    Activations Density 0.161%

    No Known Activations