© 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. 8838
    Prev
    Next
    INDEX
    Explanations

    who followed by people/actions

    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
    åįģéĩĮ
    -0.12
    å¾Īå¤ļäºĭæĥħ
    -0.10
    æĢ»è§īå¾Ĺ
    -0.10
     دائÙħا
    -0.10
    _AG
    -0.10
    ä¸Ģ家人
    -0.09
     zwar
    -0.09
    å¾Īå¤ļ人
    -0.09
    TAIL
    -0.09
    /vendor
    -0.09
    POSITIVE LOGITS
     listed
    0.09
     involved
    0.09
    æ¶īåıĬåĪ°
    0.09
     fanc
    0.09
    主æµģ
    0.08
     mentioned
    0.08
    ‘
    0.08
    æ¶īåıĬ
    0.08
     Ibid
    0.08
     ever
    0.08
    Activations Density 0.145%

    No Known Activations