© 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. 52720
    Prev
    Next
    INDEX
    Explanations

    expulsion, removal, deportation

    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
    ç¼ī
    -0.09
    _PTR
    -0.08
    èµİ
    -0.08
     bordel
    -0.08
    ickness
    -0.08
    åĤį
    -0.08
    å¼ķ
    -0.08
    èĮ§
    -0.07
    nap
    -0.07
    ief
    -0.07
    POSITIVE LOGITS
    驱
    0.13
    å¾Ģå¤ĸ
    0.13
     expulsion
    0.13
    æĴµ
    0.12
     ejected
    0.11
     expelled
    0.11
    éĢĢåĩº
    0.11
    æ»ļ
    0.10
    åĩºå±Ģ
    0.10
     khá»ıi
    0.10
    Activations Density 0.056%

    No Known Activations