© 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. 52778
    Prev
    Next
    INDEX
    Explanations

    names after "and"

    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
    çĤ¹å¤ļ
    -0.09
    å®ĥ们
    -0.09
    æ²ı
    -0.09
    ç¢Ľ
    -0.08
    æį®ç»Łè®¡
    -0.08
    å°¸
    -0.08
    ãģķãģ¦
    -0.08
    .gnu
    -0.08
    tees
    -0.08
    æľī人说
    -0.08
    POSITIVE LOGITS
    ãģĪ
    0.09
    Çİ
    0.08
     Nur
    0.08
    太éĺ³
    0.08
    åį³å°Ĩ
    0.08
    entially
    0.08
    çŃ
    0.08
    è¶³å¤ŁçļĦ
    0.08
    jian
    0.08
    è½®æµģ
    0.08
    Activations Density 0.030%

    No Known Activations