© 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. 50629
    Prev
    Next
    INDEX
    Explanations

    and ... further 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
    eworld
    -0.10
    cene
    -0.10
    UTO
    -0.09
    ائ
    -0.09
    iaux
    -0.09
    绣绣
    -0.08
    æĺ§
    -0.08
    ëĭĺ
    -0.08
    جÙĩ
    -0.08
    è°Ī
    -0.08
    POSITIVE LOGITS
    ç»ĨåĮĸ
    0.10
    è¯Ī
    0.09
    éĽķ
    0.09
    丰å¯Į
    0.09
    èIJĥ
    0.08
    æĹı
    0.08
    Phoenix
    0.08
    å¢ŀå¤ļ
    0.08
    esta
    0.08
    裹
    0.08
    Activations Density 0.069%

    No Known Activations