© 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. 52421
    Prev
    Next
    INDEX
    Explanations

    revive and revival

    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
    ç¯ļ
    -0.10
    客æ°Ķ
    -0.09
    AGER
    -0.09
    ç¼
    -0.09
    å¦ĥ
    -0.09
    åŃļ
    -0.08
    æĿı
    -0.08
    .bridge
    -0.08
    æŃ¤æ¬¡
    -0.08
    åĥ§
    -0.08
    POSITIVE LOGITS
    èĵ¼
    0.11
    åĴĮåıijå±ķ
    0.11
    OrCreate
    0.11
    ä¸İåıijå±ķ
    0.09
    èIJİ
    0.09
    ously
    0.09
     revive
    0.09
     interest
    0.09
    åı¤èĢģ
    0.09
    çıij
    0.09
    Activations Density 0.016%

    No Known Activations