© 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. 20897
    Prev
    Next
    INDEX
    Explanations

    ishment, -ly, -er, -ian

    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
     bảng
    -0.09
    便äºİ
    -0.09
    backs
    -0.09
    ä¸įæĺĵ
    -0.08
    ä¸įçĦ¶
    -0.08
    æĸij
    -0.08
    è¿Ľåĩº
    -0.08
    _ABI
    -0.08
    çĻ¾
    -0.08
    pec
    -0.08
    POSITIVE LOGITS
    ishment
    0.11
    èµĽåIJİ
    0.10
    çĤĶ
    0.10
    éķ¿å¤§
    0.09
    ç©ij
    0.09
    antly
    0.09
    querque
    0.09
     pháºŃn
    0.09
    raries
    0.09
    åĪ©äºļ
    0.09
    Activations Density 0.311%

    No Known Activations